> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mountsea.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Submit Video Task
> Generates video using the selected model. The generation mode (text-to-video / image-to-video / etc.) is determined entirely by the `model` you choose — no separate `mode` field is needed.
**Text-to-video** — pass `prompt` only:
`veo-3.1` · `veo-3.1-fast` · `veo-3.1-lite` · `veo-3` · `kling-v3-pro` · `kling-v3-standard` · `wan-2.7` · `seedance-2.0`
**Image-to-video** — pass `prompt` + `image_urls` (1 image):
`veo-3.1-image` · `veo-3.1-fast-image` · `veo-3.1-lite-image` · `veo-3-image` · `kling-v3-pro-image` · `kling-v3-standard-image` · `wan-2.7-image` · `seedance-2.0-image`
**Multi-reference video** — `image_urls` with 2–9 images:
`veo-3.1-ref` · `veo-3.1-fast-ref`
**First-last frame** — `image_urls[0]` = start frame, `image_urls[1]` = end frame:
`veo-3.1-first-last`
> Always pass image(s) via `image_urls: string[]`; the service maps them to the correct fal field automatically.
---
**Workflow**
1. `GET /hub/v1/models?capability=video` — browse available models
2. `GET /hub/v1/models/:model` — copy the `example` as your `input`
3. `POST /hub/v1/video` ← you are here
4. `GET /hub/v1/tasks/:task_id` — poll until `ready=true`
---
## Model Reference
> **Tip:** Click **Try it out** → select a model from the dropdown below → the parameter schema auto-populates with an example.
### `veo-3.1` — Veo 3.1 (Google) · `text-to-video`
Google Veo 3.1 text-to-video with optional native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | `true` | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | Aspect ratio of the generated video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3.1",
"input": {
"prompt": "Two person street interview in New York City.\nSample Dialogue:\nHost: \"Did you hear the news?\"\nPerson: \"Yes! Veo 3.1 is now available online. If you want to see it, go check it out!\"",
"auto_fix": true,
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-image` — Veo 3.1 Image-to-Video (Google) · `image-to-video`
Veo 3.1: animate a single reference image.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `image_url` | `string` | ✓ | – | – | URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The aspect ratio of the generated video. Only 16:9 and 9:16 are supported. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3.1-image",
"input": {
"prompt": "A monkey and polar bear host a casual podcast about AI inference, bringing their unique perspectives from different environments (tropical vs. arctic) to discuss how AI systems make decisions and process information.\nSample Dialogue:\nMonkey (Banana): \"Welcome back to Bananas & Ice! I am Banana\"\nPolar Bear (Ice): \"And I'm Ice!\"",
"duration": "8s",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-ref` — Veo 3.1 Multi-Ref (Google) · `reference-to-video`
Veo 3.1: generate video from reference images for consistent subject appearance.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `image_urls` | `array` | ✓ | – | – | URLs of the reference images to use for consistent subject appearance |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | The aspect ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3.1-ref",
"input": {
"prompt": "A chimpanzee wearing overalls frolics in the grassy field, gently playing with the butterflies. In the background, a circus tent and carousel beckon.",
"duration": "8s",
"image_urls": [
"https://example.com/sample-image.jpg",
"https://example.com/sample-image-2.jpg",
"https://example.com/sample-image-3.jpg"
],
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-first-last` — Veo 3.1 First-Last Frame (Google) · `first-last-frame-to-video`
Veo 3.1: generate a transition video between a start frame and an end frame.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The aspect ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `last_frame_url` | `string` | ✓ | – | – | URL of the last frame of the video |
| `first_frame_url` | `string` | ✓ | – | – | URL of the first frame of the video |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3.1-first-last",
"input": {
"prompt": "A woman looks into the camera, breathes in, then exclaims energetically, \"have you guys checked out this AI video generation? It's incredible!\"",
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"last_frame_url": "https://example.com/sample-image-2.jpg",
"first_frame_url": "https://example.com/sample-image.jpg",
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-fast` — Veo 3.1 Fast (Google) · `text-to-video`
Veo 3.1 Fast: lower-latency text-to-video at reduced cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | `true` | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | Aspect ratio of the generated video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3.1-fast",
"input": {
"prompt": "Two person street interview in New York City.\nSample Dialogue:\nHost: \"Did you hear the news?\"\nPerson: \"Yes! Veo 3.1 is now available online. If you want to see it, go check it out!\"",
"auto_fix": true,
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-fast-image` — Veo 3.1 Fast Image-to-Video (Google) · `image-to-video`
Veo 3.1 Fast: animate a reference image at lower cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `image_url` | `string` | ✓ | – | – | URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The aspect ratio of the generated video. Only 16:9 and 9:16 are supported. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3.1-fast-image",
"input": {
"prompt": "A monkey and polar bear host a casual podcast about AI inference, bringing their unique perspectives from different environments (tropical vs. arctic) to discuss how AI systems make decisions and process information.\nSample Dialogue:\nMonkey (Banana): \"Welcome back to Bananas & Ice! I am Banana\"\nPolar Bear (Ice): \"And I'm Ice!\"",
"duration": "8s",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-fast-ref` — Veo 3.1 Fast Multi-Ref (Google) · `reference-to-video`
Veo 3.1 Fast: multi-reference video at lower cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `image_urls` | `array` | ✓ | – | – | URLs of the reference images to use for consistent subject appearance |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | The aspect ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3.1-fast-ref",
"input": {
"prompt": "A chimpanzee wearing overalls frolics in the grassy field, gently playing with the butterflies. In the background, a circus tent and carousel beckon.",
"duration": "8s",
"image_urls": [
"https://example.com/sample-image.jpg",
"https://example.com/sample-image-2.jpg",
"https://example.com/sample-image-3.jpg"
],
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-lite` — Veo 3.1 Lite (Google) · `text-to-video`
Veo 3.1 Lite: lowest cost text-to-video (720p/1080p only).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | `true` | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | Aspect ratio of the generated video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3.1-lite",
"input": {
"prompt": "A massive blue whale glides through crystal-clear deep ocean water, sunlight rays piercing through the surface above, bioluminescent plankton scattered around, cinematic slow motion",
"auto_fix": true,
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-lite-image` — Veo 3.1 Lite Image-to-Video (Google) · `image-to-video`
Veo 3.1 Lite: animate a reference image at lowest cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `image_url` | `string` | ✓ | – | – | URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit. |
| `resolution` | `string` | | `720p` | `720p` `1080p` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The aspect ratio of the generated video. Only 16:9 and 9:16 are supported. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3.1-lite-image",
"input": {
"prompt": "A massive blue whale glides through crystal-clear deep ocean water, sunlight rays piercing through the surface above, bioluminescent plankton scattered around, cinematic slow motion",
"duration": "8s",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3` — Veo 3 (Google) · `text-to-video`
Google Veo 3 text-to-video with native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video you want to generate |
| `auto_fix` | `boolean` | | `true` | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | The aspect ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3",
"input": {
"prompt": "A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen Google's new Veo3 model It is a super good model. Person replies: Yeah I saw it, it's already available now. It's crazy good.",
"auto_fix": true,
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3-image` — Veo 3 Image-to-Video (Google) · `image-to-video`
Google Veo 3: animate a single reference image.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing how the image should be animated |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the generated video. |
| `image_url` | `string` | ✓ | – | – | URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit. |
| `resolution` | `string` | | `720p` | `720p` `1080p` | The resolution of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The aspect ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
```json
{
"model": "veo-3-image",
"input": {
"prompt": "A woman looks into the camera, breathes in, then exclaims energetically, \"have you guys checked out this AI video generation? It's incredible!\"",
"duration": "8s",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `kling-v3-standard` — Kling v3 Standard (Kuaishou) · `text-to-video`
Kling v3 Standard text-to-video with optional native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | | – | – | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |
| `duration` | `string` | | `5` | `3` `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | The duration of the generated video in seconds |
| `cfg_scale` | `number` | | `0.5` | – | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `shot_type` | `string` | | `customize` | `customize` `intelligent` | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` `1:1` | The aspect ratio of the generated video frame |
| `multi_prompt` | `array` | | – | – | List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |
| `negative_prompt` | `string` | | `blur, distort, and low quality` | – | – |
Example request body
```json
{
"model": "kling-v3-standard",
"input": {
"prompt": "Cinematic drone shot flying through ancient stone ruins covered in moss and vines at golden hour. Camera starts low, rises through crumbling archways, revealing a vast misty valley beyond. Volumetric light rays pierce through gaps in the stone. Epic scale, photorealistic, 8K quality.",
"duration": "5",
"cfg_scale": 0.5,
"shot_type": "customize",
"aspect_ratio": "16:9",
"multi_prompt": null,
"generate_audio": true,
"negative_prompt": "blur, distort, and low quality"
}
}
```
---
### `kling-v3-standard-image` — Kling v3 Standard Image-to-Video (Kuaishou) · `image-to-video`
Kling v3 Standard image-to-video (3-15 seconds).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | | – | – | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |
| `duration` | `string` | | `5` | `3` `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | The duration of the generated video in seconds |
| `elements` | `array` | | – | – | Elements (characters/objects) to include in the video. Each element can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc. |
| `cfg_scale` | `number` | | `0.5` | – | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `shot_type` | `string` | | `customize` | `customize` `intelligent` | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `multi_prompt` | `array` | | – | – | List of prompts for multi-shot video generation. If provided, divides the video into multiple shots. |
| `end_image_url` | `string` | | – | – | URL of the image to be used for the end of the video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |
| `negative_prompt` | `string` | | `blur, distort, and low quality` | – | – |
| `start_image_url` | `string` | ✓ | – | – | URL of the image to be used for the video |
Example request body
```json
{
"model": "kling-v3-standard-image",
"input": {
"prompt": "Camera slowly orbits around the vase. Soft light shifts across the ceramic surface. The pampas grass sways gently. Shadows move elegantly. Smooth continuous motion, premium feel.",
"duration": "12",
"cfg_scale": 0.5,
"shot_type": "customize",
"multi_prompt": null,
"generate_audio": true,
"negative_prompt": "blur, distort, and low quality",
"start_image_url": "https://example.com/sample-image.jpg"
}
}
```
---
### `kling-v3-pro` — Kling v3 Pro (Kuaishou) · `text-to-video`
Kling v3 Pro text-to-video with optional native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | | – | – | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |
| `duration` | `string` | | `5` | `3` `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | The duration of the generated video in seconds |
| `cfg_scale` | `number` | | `0.5` | – | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `shot_type` | `string` | | `customize` | `customize` `intelligent` | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` `1:1` | The aspect ratio of the generated video frame |
| `multi_prompt` | `array` | | – | – | List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |
| `negative_prompt` | `string` | | `blur, distort, and low quality` | – | – |
Example request body
```json
{
"model": "kling-v3-pro",
"input": {
"prompt": "Close-up of glowing fireflies dancing in a dark forest at twilight. Soft bioluminescent particles float through the air. Shallow depth of field, bokeh lights in background. Magical atmosphere, gentle movement.",
"duration": "5",
"cfg_scale": 0.5,
"shot_type": "customize",
"aspect_ratio": "16:9",
"multi_prompt": null,
"generate_audio": true,
"negative_prompt": "blur, distort, and low quality"
}
}
```
---
### `kling-v3-pro-image` — Kling v3 Pro Image-to-Video (Kuaishou) · `image-to-video`
Kling v3 Pro image-to-video (3-15 seconds).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | | – | – | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |
| `duration` | `string` | | `5` | `3` `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | The duration of the generated video in seconds |
| `elements` | `array` | | – | – | Elements (characters/objects) to include in the video. Each element can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc. |
| `cfg_scale` | `number` | | `0.5` | – | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `shot_type` | `string` | | `customize` | `customize` `intelligent` | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `multi_prompt` | `array` | | – | – | List of prompts for multi-shot video generation. If provided, divides the video into multiple shots. |
| `end_image_url` | `string` | | – | – | URL of the image to be used for the end of the video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |
| `negative_prompt` | `string` | | `blur, distort, and low quality` | – | – |
| `start_image_url` | `string` | ✓ | – | – | URL of the image to be used for the video |
Example request body
```json
{
"model": "kling-v3-pro-image",
"input": {
"prompt": "The craftsman slowly examines the bowl, turning it gently in his weathered hands. His eyes reflect years of wisdom. Subtle smile forms on his face. Dust particles drift in warm light. Breathing motion, blinking eyes.",
"duration": "12",
"cfg_scale": 0.5,
"shot_type": "customize",
"multi_prompt": null,
"generate_audio": true,
"negative_prompt": "blur, distort, and low quality",
"start_image_url": "https://example.com/sample-image.jpg"
}
}
```
---
### `wan-2.7` — WAN 2.7 (Alibaba) · `text-to-video`
WAN 2.7 text-to-video - high quality generation. Default resolution is 1080p.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility (0-2147483647). |
| `prompt` | `string` | ✓ | – | – | Text prompt describing the desired video. Max 5000 characters. |
| `duration` | `integer` | | `5` | `2` `3` `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | Output video duration in seconds (2-15). |
| `audio_url` | `string` | | – | – | URL of driving audio. Supports WAV and MP3. Duration: 3-30s. Max 15 MB. If not provided, the model auto-generates matching background music. |
| `resolution` | `string` | | `1080p` | `720p` `1080p` | Output video resolution tier. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` `1:1` `4:3` `3:4` | Aspect ratio of the generated video. |
| `negative_prompt` | `string` | | – | – | Content to avoid in the video. Max 500 characters. |
| `enable_safety_checker` | `boolean` | | `true` | – | Enable content moderation for input and output. |
| `enable_prompt_expansion` | `boolean` | | `true` | – | Enable intelligent prompt rewriting. |
Example request body
```json
{
"model": "wan-2.7",
"input": {
"prompt": "A kitten running in a meadow, cinematic lighting, smooth camera movement.",
"duration": 5,
"resolution": "1080p",
"aspect_ratio": "16:9",
"negative_prompt": "low resolution, errors, worst quality, low quality",
"enable_safety_checker": true,
"enable_prompt_expansion": true
}
}
```
---
### `wan-2.7-image` — WAN 2.7 Image-to-Video (Alibaba) · `image-to-video`
WAN 2.7 image-to-video (720p/1080p, duration 2-15s).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility (0-2147483647). |
| `prompt` | `string` | | – | – | Text prompt describing the desired video. Max 5000 characters. |
| `duration` | `integer` | | `5` | `2` `3` `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | Output video duration in seconds (2-15). |
| `audio_url` | `string` | | – | – | URL of driving audio. Supports WAV and MP3. Duration: 2-30s. Max 15 MB. |
| `image_url` | `string` | | – | – | URL of the first frame image. Formats: JPEG, JPG, PNG, BMP, WEBP. Max 20 MB. |
| `video_url` | `string` | | – | – | URL of a video clip to continue from. Format: MP4, MOV. Duration: 2-10s. Max 100 MB. Cannot be combined with image_url. |
| `resolution` | `string` | | `1080p` | `720p` `1080p` | Output video resolution tier. |
| `end_image_url` | `string` | | – | – | URL of the last frame image for first-and-last-frame-to-video. Same constraints as image_url. |
| `negative_prompt` | `string` | | – | – | Content to avoid in the video. Max 500 characters. |
| `enable_safety_checker` | `boolean` | | `true` | – | Enable content moderation for input and output. |
| `enable_prompt_expansion` | `boolean` | | `true` | – | Enable intelligent prompt rewriting. |
Example request body
```json
{
"model": "wan-2.7-image",
"input": {
"prompt": "The massive humpback whale glides slowly through the deep blue water. It turns gracefully, its huge pectoral fin sweeping through the water like a wing. Sunbeams penetrate from above, illuminating the whale's textured skin. Small fish scatter. Awe-inspiring scale and grace.",
"duration": 5,
"image_url": "https://example.com/sample-image.jpg",
"resolution": "1080p",
"negative_prompt": "low resolution, errors, worst quality, low quality, incomplete, extra fingers, bad proportions, blurry, distorted",
"enable_safety_checker": true,
"enable_prompt_expansion": true
}
}
```
---
### `wan-2.7-ref` — WAN 2.7 Reference-to-Video (Alibaba) · `reference-to-video`
WAN 2.7 reference-to-video using character/object reference images and videos (duration 2-10s).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility (0-2147483647). |
| `prompt` | `string` | ✓ | – | – | Text prompt describing the desired video. Max 5000 characters. |
| `duration` | `integer` | | `5` | `2` `3` `4` `5` `6` `7` `8` `9` `10` | Output video duration in seconds (2-10). |
| `resolution` | `string` | | `1080p` | `720p` `1080p` | Output video resolution tier. |
| `multi_shots` | `boolean` | | `false` | – | When true, enables intelligent multi-shot segmentation. When false (default), generates a single continuous shot. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` `1:1` `4:3` `3:4` | Aspect ratio of the generated video. |
| `negative_prompt` | `string` | | – | – | Content to avoid in the video. Max 500 characters. |
| `reference_image_urls` | `array` | | – | – | Reference image URLs for character/object appearance. Pass multiple images for multi-subject generation. Max 20 MB each. |
| `reference_video_urls` | `array` | | – | – | Reference video URLs for character/object appearance and motion. Pass multiple videos for multi-subject generation. Max 100 MB each. Note: when video inputs are provided, billing includes the total input video duration plus the output duration. Your charged credits will be higher than the output duration alone. |
| `enable_safety_checker` | `boolean` | | `true` | – | Enable content moderation for input and output. |
Example request body
```json
{
"model": "wan-2.7-ref",
"input": {
"prompt": "A person walking through a beautiful garden, cinematic style.",
"duration": 5,
"resolution": "1080p",
"aspect_ratio": "16:9",
"negative_prompt": "low resolution, errors, worst quality, low quality",
"enable_safety_checker": true
}
}
```
---
### `wan-2.7-edit` — WAN 2.7 Edit Video (Alibaba) · `video-to-video`
WAN 2.7 video editing: instruction-based editing, reference-image-based editing and style transfer (input video 2-10s).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility (0-2147483647). |
| `prompt` | `string` | ✓ | – | – | Editing instruction or style transfer description. Describe what changes you want applied to the video. |
| `duration` | `string` | | `0` | `0` `2` `3` `4` `5` `6` `7` `8` `9` `10` | Output duration in seconds. '0' means match the input video's duration. When set to 2-10, the output is truncated to that length from the start. |
| `video_url` | `string` | ✓ | – | – | URL of the input video to edit. Format: MP4, MOV. Duration: 2-10s. Max 100 MB. |
| `resolution` | `string` | | `1080p` | `720p` `1080p` | Output video resolution tier. |
| `aspect_ratio` | `string` | | – | `16:9` `9:16` `1:1` `4:3` `3:4` | Aspect ratio of the output video. If not provided, uses the input video's aspect ratio. |
| `audio_setting` | `string` | | `auto` | `auto` `origin` | Audio handling: 'auto' lets the model decide whether to regenerate audio; 'origin' preserves the original audio from the input video. |
| `reference_image_url` | `string` | | – | – | Optional reference image URL for reference-based editing. When provided, the edit is guided by the visual style or content of this image. |
| `enable_safety_checker` | `boolean` | | `true` | – | Enable content moderation for input and output. |
Example request body
```json
{
"model": "wan-2.7-edit",
"input": {
"prompt": "Transform the entire scene into a beautiful watercolor painting style. Soft brushstrokes, flowing paint washes, visible paper texture. Colors should bleed and blend naturally like wet watercolor on paper.",
"video_url": "https://example.com/sample-video.mp4",
"resolution": "1080p",
"audio_setting": "auto",
"enable_safety_checker": true
}
}
```
---
### `seedance-2.0` — Seedance 2.0 (ByteDance) · `text-to-video`
ByteDance Seedance 2.0: cinematic text-to-video with native audio, physics, and camera control.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt used to generate the video |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `resolution` | `string` | | `720p` | `480p` `720p` `1080p` | Video resolution - 480p for faster generation, 720p for balance, 1080p for highest quality. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3` `1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-image` — Seedance 2.0 Image-to-Video (ByteDance) · `image-to-video`
ByteDance Seedance 2.0: animate images with cinematic quality and synchronized audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the desired motion and action for the video. |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `image_url` | `string` | ✓ | – | – | The URL of the starting frame image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
| `resolution` | `string` | | `720p` | `480p` `720p` `1080p` | Video resolution - 480p for faster generation, 720p for balance, 1080p for highest quality. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3` `1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to infer from the input image. |
| `end_image_url` | `string` | | – | – | The URL of the image to use as the last frame of the video. When provided, the generated video will transition from the starting image to this ending image. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-image",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-ref` — Seedance 2.0 Reference-to-Video (ByteDance) · `reference-to-video`
ByteDance Seedance 2.0: generate video from reference images, videos, and audio clips.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt used to generate the video. |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `audio_urls` | `array` | | – | – | Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one reference image or video is required. |
| `image_urls` | `array` | | – | – | Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12. |
| `resolution` | `string` | | `720p` | `480p` `720p` `1080p` | Video resolution - 480p for faster generation, 720p for balance, 1080p for highest quality. |
| `video_urls` | `array` | | – | – | Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3` `1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-ref",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"image_urls": [
"https://example.com/sample-image.jpg"
],
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-fast` — Seedance 2.0 Fast (ByteDance) · `text-to-video`
ByteDance Seedance 2.0 fast tier: lower-latency text-to-video with native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt used to generate the video |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `resolution` | `string` | | `720p` | `480p` `720p` | Video resolution - 480p for faster generation, 720p for balance. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3` `1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-fast",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-fast-image` — Seedance 2.0 Fast Image-to-Video (ByteDance) · `image-to-video`
ByteDance Seedance 2.0 fast tier: lower-latency image-to-video with synchronized audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the desired motion and action for the video. |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `image_url` | `string` | ✓ | – | – | The URL of the starting frame image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
| `resolution` | `string` | | `720p` | `480p` `720p` | Video resolution - 480p for faster generation, 720p for balance. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3` `1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to infer from the input image. |
| `end_image_url` | `string` | | – | – | The URL of the image to use as the last frame of the video. When provided, the generated video will transition from the starting image to this ending image. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-fast-image",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-fast-ref` — Seedance 2.0 Fast Reference-to-Video (ByteDance) · `reference-to-video`
ByteDance Seedance 2.0 fast tier: reference-to-video with lower latency and cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt used to generate the video. |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11` `12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `audio_urls` | `array` | | – | – | Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one reference image or video is required. |
| `image_urls` | `array` | | – | – | Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12. |
| `resolution` | `string` | | `720p` | `480p` `720p` | Video resolution - 480p for faster generation, 720p for balance. |
| `video_urls` | `array` | | – | – | Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3` `1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-fast-ref",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"image_urls": [
"https://example.com/sample-image.jpg"
],
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
## OpenAPI
````yaml POST /hub/v1/video
openapi: 3.0.0
info:
title: Hub - Premium AI Gateway (Image / Video / Audio / Transcribe)
description: >-
Hub is a unified AI Gateway offering **flagship-quality, production-stable,
and cheaper-than-official** access to the world's best AI models across
image, video, audio (music) and transcription capabilities.
**Why Hub?**
- 🏆 **Flagship quality** — only official flagship model weights (Veo 3.1,
Nano Banana Pro, GPT Image 2, Kling v3 Pro, WAN 2.7, Seedance 2.0,
ElevenLabs Music). No knock-offs, no distillations — same outputs as going
direct.
- 🛡️ **Production stable** — multi-region routing, automatic failover,
transparent retries on transient errors, queue-aware load balancing. Built
for 24/7 production traffic.
- 💰 **Cheaper than official** — pay only on `status=completed` (failed
tasks are free), billed in unified credits at a meaningful discount versus
going direct to the model provider. No per-provider minimums, no monthly
subscriptions.
Each endpoint accepts a `model` + `input` payload — switch models without
changing the endpoint shape.
version: 1.0.0
contact: {}
servers:
- url: https://api.mountsea.ai
description: API Gateway
security: []
tags:
- name: hub
description: >-
Model discovery — list and inspect schemas/examples for every available
model across all capabilities.
- name: Image
description: >-
Image generation & editing models (Nano Banana, GPT Image 2 and edit
variants).
- name: Video
description: >-
Video generation models — text-to-video, image-to-video, multi-reference,
first-last frame and edit (Veo 3.1, Kling v3, WAN 2.7, Seedance 2.0).
- name: Audio
description: >-
Audio capabilities — music generation (ElevenLabs Music) and audio/video
transcription.
- name: Tasks
description: Poll the status / result of any submitted Hub task.
paths:
/hub/v1/video:
post:
tags:
- Video
summary: Submit a video generation task
description: >
Generates video using the selected model. The generation mode
(text-to-video / image-to-video / etc.) is determined entirely by the
`model` you choose — no separate `mode` field is needed.
**Text-to-video** — pass `prompt` only:
`veo-3.1` · `veo-3.1-fast` · `veo-3.1-lite` · `veo-3` · `kling-v3-pro` ·
`kling-v3-standard` · `wan-2.7` · `seedance-2.0`
**Image-to-video** — pass `prompt` + `image_urls` (1 image):
`veo-3.1-image` · `veo-3.1-fast-image` · `veo-3.1-lite-image` ·
`veo-3-image` · `kling-v3-pro-image` · `kling-v3-standard-image` ·
`wan-2.7-image` · `seedance-2.0-image`
**Multi-reference video** — `image_urls` with 2–9 images:
`veo-3.1-ref` · `veo-3.1-fast-ref`
**First-last frame** — `image_urls[0]` = start frame, `image_urls[1]` =
end frame:
`veo-3.1-first-last`
> Always pass image(s) via `image_urls: string[]`; the service maps them
to the correct fal field automatically.
---
**Workflow**
1. `GET /hub/v1/models?capability=video` — browse available models
2. `GET /hub/v1/models/:model` — copy the `example` as your `input`
3. `POST /hub/v1/video` ← you are here
4. `GET /hub/v1/tasks/:task_id` — poll until `ready=true`
---
## Model Reference
> **Tip:** Click **Try it out** → select a model from the dropdown below
→ the parameter schema auto-populates with an example.
### `veo-3.1` — Veo 3.1 (Google) · `text-to-video`
Google Veo 3.1 text-to-video with optional native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number
generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | `true` | – | Whether to automatically
attempt to fix prompts that fail content policy or other validation
checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The
resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | Aspect ratio
of the generated video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide
the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3.1",
"input": {
"prompt": "Two person street interview in New York City.\nSample Dialogue:\nHost: \"Did you hear the news?\"\nPerson: \"Yes! Veo 3.1 is now available online. If you want to see it, go check it out!\"",
"auto_fix": true,
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-image` — Veo 3.1 Image-to-Video (Google) · `image-to-video`
Veo 3.1: animate a single reference image.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number
generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt
to fix prompts that fail content policy or other validation checks by
rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `image_url` | `string` | ✓ | – | – | URL of the input image to
animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect
ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be
cropped to fit. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The
resolution of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The
aspect ratio of the generated video. Only 16:9 and 9:16 are supported. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide
the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3.1-image",
"input": {
"prompt": "A monkey and polar bear host a casual podcast about AI inference, bringing their unique perspectives from different environments (tropical vs. arctic) to discuss how AI systems make decisions and process information.\nSample Dialogue:\nMonkey (Banana): \"Welcome back to Bananas & Ice! I am Banana\"\nPolar Bear (Ice): \"And I'm Ice!\"",
"duration": "8s",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-ref` — Veo 3.1 Multi-Ref (Google) · `reference-to-video`
Veo 3.1: generate video from reference images for consistent subject
appearance.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt
to fix prompts that fail content policy or other validation checks by
rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `image_urls` | `array` | ✓ | – | – | URLs of the reference images to
use for consistent subject appearance |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The
resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | The aspect
ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3.1-ref",
"input": {
"prompt": "A chimpanzee wearing overalls frolics in the grassy field, gently playing with the butterflies. In the background, a circus tent and carousel beckon.",
"duration": "8s",
"image_urls": [
"https://example.com/sample-image.jpg",
"https://example.com/sample-image-2.jpg",
"https://example.com/sample-image-3.jpg"
],
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-first-last` — Veo 3.1 First-Last Frame (Google) ·
`first-last-frame-to-video`
Veo 3.1: generate a transition video between a start frame and an end
frame.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number
generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt
to fix prompts that fail content policy or other validation checks by
rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The
resolution of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The
aspect ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `last_frame_url` | `string` | ✓ | – | – | URL of the last frame of the
video |
| `first_frame_url` | `string` | ✓ | – | – | URL of the first frame of
the video |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide
the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3.1-first-last",
"input": {
"prompt": "A woman looks into the camera, breathes in, then exclaims energetically, \"have you guys checked out this AI video generation? It's incredible!\"",
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"last_frame_url": "https://example.com/sample-image-2.jpg",
"first_frame_url": "https://example.com/sample-image.jpg",
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-fast` — Veo 3.1 Fast (Google) · `text-to-video`
Veo 3.1 Fast: lower-latency text-to-video at reduced cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number
generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | `true` | – | Whether to automatically
attempt to fix prompts that fail content policy or other validation
checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The
resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | Aspect ratio
of the generated video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide
the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3.1-fast",
"input": {
"prompt": "Two person street interview in New York City.\nSample Dialogue:\nHost: \"Did you hear the news?\"\nPerson: \"Yes! Veo 3.1 is now available online. If you want to see it, go check it out!\"",
"auto_fix": true,
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-fast-image` — Veo 3.1 Fast Image-to-Video (Google) ·
`image-to-video`
Veo 3.1 Fast: animate a reference image at lower cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number
generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt
to fix prompts that fail content policy or other validation checks by
rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `image_url` | `string` | ✓ | – | – | URL of the input image to
animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect
ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be
cropped to fit. |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The
resolution of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The
aspect ratio of the generated video. Only 16:9 and 9:16 are supported. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide
the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3.1-fast-image",
"input": {
"prompt": "A monkey and polar bear host a casual podcast about AI inference, bringing their unique perspectives from different environments (tropical vs. arctic) to discuss how AI systems make decisions and process information.\nSample Dialogue:\nMonkey (Banana): \"Welcome back to Bananas & Ice! I am Banana\"\nPolar Bear (Ice): \"And I'm Ice!\"",
"duration": "8s",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-fast-ref` — Veo 3.1 Fast Multi-Ref (Google) ·
`reference-to-video`
Veo 3.1 Fast: multi-reference video at lower cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt
to fix prompts that fail content policy or other validation checks by
rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `image_urls` | `array` | ✓ | – | – | URLs of the reference images to
use for consistent subject appearance |
| `resolution` | `string` | | `720p` | `720p` `1080p` `4k` | The
resolution of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | The aspect
ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3.1-fast-ref",
"input": {
"prompt": "A chimpanzee wearing overalls frolics in the grassy field, gently playing with the butterflies. In the background, a circus tent and carousel beckon.",
"duration": "8s",
"image_urls": [
"https://example.com/sample-image.jpg",
"https://example.com/sample-image-2.jpg",
"https://example.com/sample-image-3.jpg"
],
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-lite` — Veo 3.1 Lite (Google) · `text-to-video`
Veo 3.1 Lite: lowest cost text-to-video (720p/1080p only).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number
generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | `true` | – | Whether to automatically
attempt to fix prompts that fail content policy or other validation
checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` | The resolution
of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | Aspect ratio
of the generated video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide
the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3.1-lite",
"input": {
"prompt": "A massive blue whale glides through crystal-clear deep ocean water, sunlight rays piercing through the surface above, bioluminescent plankton scattered around, cinematic slow motion",
"auto_fix": true,
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3.1-lite-image` — Veo 3.1 Lite Image-to-Video (Google) ·
`image-to-video`
Veo 3.1 Lite: animate a reference image at lowest cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number
generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt
to fix prompts that fail content policy or other validation checks by
rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `image_url` | `string` | ✓ | – | – | URL of the input image to
animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect
ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be
cropped to fit. |
| `resolution` | `string` | | `720p` | `720p` `1080p` | The resolution
of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The
aspect ratio of the generated video. Only 16:9 and 9:16 are supported. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide
the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3.1-lite-image",
"input": {
"prompt": "A massive blue whale glides through crystal-clear deep ocean water, sunlight rays piercing through the surface above, bioluminescent plankton scattered around, cinematic slow motion",
"duration": "8s",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3` — Veo 3 (Google) · `text-to-video`
Google Veo 3 text-to-video with native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number
generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the video
you want to generate |
| `auto_fix` | `boolean` | | `true` | – | Whether to automatically
attempt to fix prompts that fail content policy or other validation
checks by rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `resolution` | `string` | | `720p` | `720p` `1080p` | The resolution
of the generated video. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` | The aspect
ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide
the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3",
"input": {
"prompt": "A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen Google's new Veo3 model It is a super good model. Person replies: Yeah I saw it, it's already available now. It's crazy good.",
"auto_fix": true,
"duration": "8s",
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `veo-3-image` — Veo 3 Image-to-Video (Google) · `image-to-video`
Google Veo 3: animate a single reference image.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | The seed for the random number
generator. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing how the
image should be animated |
| `auto_fix` | `boolean` | | – | – | Whether to automatically attempt
to fix prompts that fail content policy or other validation checks by
rewriting them. |
| `duration` | `string` | | `8s` | `4s` `6s` `8s` | The duration of the
generated video. |
| `image_url` | `string` | ✓ | – | – | URL of the input image to
animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect
ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be
cropped to fit. |
| `resolution` | `string` | | `720p` | `720p` `1080p` | The resolution
of the generated video. |
| `aspect_ratio` | `string` | | `auto` | `auto` `16:9` `9:16` | The
aspect ratio of the generated video. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
audio for the video. |
| `negative_prompt` | `string` | | – | – | A negative prompt to guide
the video generation. |
| `safety_tolerance` | `string` | | `4` | `1` `2` `3` `4` `5` `6` | The
safety tolerance level for content moderation. 1 is the most strict
(blocks most content), 6 is the least strict. Note: API-only parameter.
|
Example request body
```json
{
"model": "veo-3-image",
"input": {
"prompt": "A woman looks into the camera, breathes in, then exclaims energetically, \"have you guys checked out this AI video generation? It's incredible!\"",
"duration": "8s",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true,
"safety_tolerance": "4"
}
}
```
---
### `kling-v3-standard` — Kling v3 Standard (Kuaishou) · `text-to-video`
Kling v3 Standard text-to-video with optional native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | | – | – | Text prompt for video generation.
Either prompt or multi_prompt must be provided, but not both. |
| `duration` | `string` | | `5` | `3` `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | The duration of the generated video in seconds |
| `cfg_scale` | `number` | | `0.5` | – | The CFG (Classifier Free
Guidance) scale is a measure of how close you want the model to stick to
your prompt. |
| `shot_type` | `string` | | `customize` | `customize` `intelligent` |
The type of multi-shot video generation. 'intelligent' lets the model
automatically determine shot structure. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` `1:1` | The
aspect ratio of the generated video frame |
| `multi_prompt` | `array` | | – | – | List of prompts for multi-shot
video generation. If provided, overrides the single prompt and divides
the video into multiple shots with specified prompts and durations. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
native audio for the video. Supports Chinese and English voice output.
Other languages are automatically translated to English. For English
speech, use lowercase letters; for acronyms or proper nouns, use
uppercase. |
| `negative_prompt` | `string` | | `blur, distort, and low quality` | –
| – |
Example request body
```json
{
"model": "kling-v3-standard",
"input": {
"prompt": "Cinematic drone shot flying through ancient stone ruins covered in moss and vines at golden hour. Camera starts low, rises through crumbling archways, revealing a vast misty valley beyond. Volumetric light rays pierce through gaps in the stone. Epic scale, photorealistic, 8K quality.",
"duration": "5",
"cfg_scale": 0.5,
"shot_type": "customize",
"aspect_ratio": "16:9",
"multi_prompt": null,
"generate_audio": true,
"negative_prompt": "blur, distort, and low quality"
}
}
```
---
### `kling-v3-standard-image` — Kling v3 Standard Image-to-Video
(Kuaishou) · `image-to-video`
Kling v3 Standard image-to-video (3-15 seconds).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | | – | – | Text prompt for video generation.
Either prompt or multi_prompt must be provided, but not both. |
| `duration` | `string` | | `5` | `3` `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | The duration of the generated video in seconds |
| `elements` | `array` | | – | – | Elements (characters/objects) to
include in the video. Each element can either be an image set (frontal +
reference images) or a video. Reference in prompt as @Element1,
@Element2, etc. |
| `cfg_scale` | `number` | | `0.5` | – | The CFG (Classifier Free
Guidance) scale is a measure of how close you want the model to stick to
your prompt. |
| `shot_type` | `string` | | `customize` | `customize` `intelligent` |
The type of multi-shot video generation. 'intelligent' lets the model
automatically determine shot structure. |
| `multi_prompt` | `array` | | – | – | List of prompts for multi-shot
video generation. If provided, divides the video into multiple shots. |
| `end_image_url` | `string` | | – | – | URL of the image to be used
for the end of the video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
native audio for the video. Supports Chinese and English voice output.
Other languages are automatically translated to English. For English
speech, use lowercase letters; for acronyms or proper nouns, use
uppercase. |
| `negative_prompt` | `string` | | `blur, distort, and low quality` | –
| – |
| `start_image_url` | `string` | ✓ | – | – | URL of the image to be used
for the video |
Example request body
```json
{
"model": "kling-v3-standard-image",
"input": {
"prompt": "Camera slowly orbits around the vase. Soft light shifts across the ceramic surface. The pampas grass sways gently. Shadows move elegantly. Smooth continuous motion, premium feel.",
"duration": "12",
"cfg_scale": 0.5,
"shot_type": "customize",
"multi_prompt": null,
"generate_audio": true,
"negative_prompt": "blur, distort, and low quality",
"start_image_url": "https://example.com/sample-image.jpg"
}
}
```
---
### `kling-v3-pro` — Kling v3 Pro (Kuaishou) · `text-to-video`
Kling v3 Pro text-to-video with optional native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | | – | – | Text prompt for video generation.
Either prompt or multi_prompt must be provided, but not both. |
| `duration` | `string` | | `5` | `3` `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | The duration of the generated video in seconds |
| `cfg_scale` | `number` | | `0.5` | – | The CFG (Classifier Free
Guidance) scale is a measure of how close you want the model to stick to
your prompt. |
| `shot_type` | `string` | | `customize` | `customize` `intelligent` |
The type of multi-shot video generation. 'intelligent' lets the model
automatically determine shot structure. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` `1:1` | The
aspect ratio of the generated video frame |
| `multi_prompt` | `array` | | – | – | List of prompts for multi-shot
video generation. If provided, overrides the single prompt and divides
the video into multiple shots with specified prompts and durations. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
native audio for the video. Supports Chinese and English voice output.
Other languages are automatically translated to English. For English
speech, use lowercase letters; for acronyms or proper nouns, use
uppercase. |
| `negative_prompt` | `string` | | `blur, distort, and low quality` | –
| – |
Example request body
```json
{
"model": "kling-v3-pro",
"input": {
"prompt": "Close-up of glowing fireflies dancing in a dark forest at twilight. Soft bioluminescent particles float through the air. Shallow depth of field, bokeh lights in background. Magical atmosphere, gentle movement.",
"duration": "5",
"cfg_scale": 0.5,
"shot_type": "customize",
"aspect_ratio": "16:9",
"multi_prompt": null,
"generate_audio": true,
"negative_prompt": "blur, distort, and low quality"
}
}
```
---
### `kling-v3-pro-image` — Kling v3 Pro Image-to-Video (Kuaishou) ·
`image-to-video`
Kling v3 Pro image-to-video (3-15 seconds).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `prompt` | `string` | | – | – | Text prompt for video generation.
Either prompt or multi_prompt must be provided, but not both. |
| `duration` | `string` | | `5` | `3` `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | The duration of the generated video in seconds |
| `elements` | `array` | | – | – | Elements (characters/objects) to
include in the video. Each element can either be an image set (frontal +
reference images) or a video. Reference in prompt as @Element1,
@Element2, etc. |
| `cfg_scale` | `number` | | `0.5` | – | The CFG (Classifier Free
Guidance) scale is a measure of how close you want the model to stick to
your prompt. |
| `shot_type` | `string` | | `customize` | `customize` `intelligent` |
The type of multi-shot video generation. 'intelligent' lets the model
automatically determine shot structure. |
| `multi_prompt` | `array` | | – | – | List of prompts for multi-shot
video generation. If provided, divides the video into multiple shots. |
| `end_image_url` | `string` | | – | – | URL of the image to be used
for the end of the video |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
native audio for the video. Supports Chinese and English voice output.
Other languages are automatically translated to English. For English
speech, use lowercase letters; for acronyms or proper nouns, use
uppercase. |
| `negative_prompt` | `string` | | `blur, distort, and low quality` | –
| – |
| `start_image_url` | `string` | ✓ | – | – | URL of the image to be used
for the video |
Example request body
```json
{
"model": "kling-v3-pro-image",
"input": {
"prompt": "The craftsman slowly examines the bowl, turning it gently in his weathered hands. His eyes reflect years of wisdom. Subtle smile forms on his face. Dust particles drift in warm light. Breathing motion, blinking eyes.",
"duration": "12",
"cfg_scale": 0.5,
"shot_type": "customize",
"multi_prompt": null,
"generate_audio": true,
"negative_prompt": "blur, distort, and low quality",
"start_image_url": "https://example.com/sample-image.jpg"
}
}
```
---
### `wan-2.7` — WAN 2.7 (Alibaba) · `text-to-video`
WAN 2.7 text-to-video - high quality generation. Default resolution is
1080p.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility
(0-2147483647). |
| `prompt` | `string` | ✓ | – | – | Text prompt describing the desired
video. Max 5000 characters. |
| `duration` | `integer` | | `5` | `2` `3` `4` `5` `6` `7` `8` `9` `10`
`11` `12` `13` `14` `15` | Output video duration in seconds (2-15). |
| `audio_url` | `string` | | – | – | URL of driving audio. Supports WAV
and MP3. Duration: 3-30s. Max 15 MB. If not provided, the model
auto-generates matching background music. |
| `resolution` | `string` | | `1080p` | `720p` `1080p` | Output video
resolution tier. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` `1:1` `4:3`
`3:4` | Aspect ratio of the generated video. |
| `negative_prompt` | `string` | | – | – | Content to avoid in the
video. Max 500 characters. |
| `enable_safety_checker` | `boolean` | | `true` | – | Enable content
moderation for input and output. |
| `enable_prompt_expansion` | `boolean` | | `true` | – | Enable
intelligent prompt rewriting. |
Example request body
```json
{
"model": "wan-2.7",
"input": {
"prompt": "A kitten running in a meadow, cinematic lighting, smooth camera movement.",
"duration": 5,
"resolution": "1080p",
"aspect_ratio": "16:9",
"negative_prompt": "low resolution, errors, worst quality, low quality",
"enable_safety_checker": true,
"enable_prompt_expansion": true
}
}
```
---
### `wan-2.7-image` — WAN 2.7 Image-to-Video (Alibaba) ·
`image-to-video`
WAN 2.7 image-to-video (720p/1080p, duration 2-15s).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility
(0-2147483647). |
| `prompt` | `string` | | – | – | Text prompt describing the desired
video. Max 5000 characters. |
| `duration` | `integer` | | `5` | `2` `3` `4` `5` `6` `7` `8` `9` `10`
`11` `12` `13` `14` `15` | Output video duration in seconds (2-15). |
| `audio_url` | `string` | | – | – | URL of driving audio. Supports WAV
and MP3. Duration: 2-30s. Max 15 MB. |
| `image_url` | `string` | | – | – | URL of the first frame image.
Formats: JPEG, JPG, PNG, BMP, WEBP. Max 20 MB. |
| `video_url` | `string` | | – | – | URL of a video clip to continue
from. Format: MP4, MOV. Duration: 2-10s. Max 100 MB. Cannot be combined
with image_url. |
| `resolution` | `string` | | `1080p` | `720p` `1080p` | Output video
resolution tier. |
| `end_image_url` | `string` | | – | – | URL of the last frame image
for first-and-last-frame-to-video. Same constraints as image_url. |
| `negative_prompt` | `string` | | – | – | Content to avoid in the
video. Max 500 characters. |
| `enable_safety_checker` | `boolean` | | `true` | – | Enable content
moderation for input and output. |
| `enable_prompt_expansion` | `boolean` | | `true` | – | Enable
intelligent prompt rewriting. |
Example request body
```json
{
"model": "wan-2.7-image",
"input": {
"prompt": "The massive humpback whale glides slowly through the deep blue water. It turns gracefully, its huge pectoral fin sweeping through the water like a wing. Sunbeams penetrate from above, illuminating the whale's textured skin. Small fish scatter. Awe-inspiring scale and grace.",
"duration": 5,
"image_url": "https://example.com/sample-image.jpg",
"resolution": "1080p",
"negative_prompt": "low resolution, errors, worst quality, low quality, incomplete, extra fingers, bad proportions, blurry, distorted",
"enable_safety_checker": true,
"enable_prompt_expansion": true
}
}
```
---
### `wan-2.7-ref` — WAN 2.7 Reference-to-Video (Alibaba) ·
`reference-to-video`
WAN 2.7 reference-to-video using character/object reference images and
videos (duration 2-10s).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility
(0-2147483647). |
| `prompt` | `string` | ✓ | – | – | Text prompt describing the desired
video. Max 5000 characters. |
| `duration` | `integer` | | `5` | `2` `3` `4` `5` `6` `7` `8` `9` `10`
| Output video duration in seconds (2-10). |
| `resolution` | `string` | | `1080p` | `720p` `1080p` | Output video
resolution tier. |
| `multi_shots` | `boolean` | | `false` | – | When true, enables
intelligent multi-shot segmentation. When false (default), generates a
single continuous shot. |
| `aspect_ratio` | `string` | | `16:9` | `16:9` `9:16` `1:1` `4:3`
`3:4` | Aspect ratio of the generated video. |
| `negative_prompt` | `string` | | – | – | Content to avoid in the
video. Max 500 characters. |
| `reference_image_urls` | `array` | | – | – | Reference image URLs for
character/object appearance. Pass multiple images for multi-subject
generation. Max 20 MB each. |
| `reference_video_urls` | `array` | | – | – | Reference video URLs for
character/object appearance and motion. Pass multiple videos for
multi-subject generation. Max 100 MB each. Note: when video inputs are
provided, billing includes the total input video duration plus the
output duration. Your charged credits will be higher than the output
duration alone. |
| `enable_safety_checker` | `boolean` | | `true` | – | Enable content
moderation for input and output. |
Example request body
```json
{
"model": "wan-2.7-ref",
"input": {
"prompt": "A person walking through a beautiful garden, cinematic style.",
"duration": 5,
"resolution": "1080p",
"aspect_ratio": "16:9",
"negative_prompt": "low resolution, errors, worst quality, low quality",
"enable_safety_checker": true
}
}
```
---
### `wan-2.7-edit` — WAN 2.7 Edit Video (Alibaba) · `video-to-video`
WAN 2.7 video editing: instruction-based editing, reference-image-based
editing and style transfer (input video 2-10s).
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility
(0-2147483647). |
| `prompt` | `string` | ✓ | – | – | Editing instruction or style
transfer description. Describe what changes you want applied to the
video. |
| `duration` | `string` | | `0` | `0` `2` `3` `4` `5` `6` `7` `8` `9`
`10` | Output duration in seconds. '0' means match the input video's
duration. When set to 2-10, the output is truncated to that length from
the start. |
| `video_url` | `string` | ✓ | – | – | URL of the input video to edit.
Format: MP4, MOV. Duration: 2-10s. Max 100 MB. |
| `resolution` | `string` | | `1080p` | `720p` `1080p` | Output video
resolution tier. |
| `aspect_ratio` | `string` | | – | `16:9` `9:16` `1:1` `4:3` `3:4` |
Aspect ratio of the output video. If not provided, uses the input
video's aspect ratio. |
| `audio_setting` | `string` | | `auto` | `auto` `origin` | Audio
handling: 'auto' lets the model decide whether to regenerate audio;
'origin' preserves the original audio from the input video. |
| `reference_image_url` | `string` | | – | – | Optional reference image
URL for reference-based editing. When provided, the edit is guided by
the visual style or content of this image. |
| `enable_safety_checker` | `boolean` | | `true` | – | Enable content
moderation for input and output. |
Example request body
```json
{
"model": "wan-2.7-edit",
"input": {
"prompt": "Transform the entire scene into a beautiful watercolor painting style. Soft brushstrokes, flowing paint washes, visible paper texture. Colors should bleed and blend naturally like wet watercolor on paper.",
"video_url": "https://example.com/sample-video.mp4",
"resolution": "1080p",
"audio_setting": "auto",
"enable_safety_checker": true
}
}
```
---
### `seedance-2.0` — Seedance 2.0 (ByteDance) · `text-to-video`
ByteDance Seedance 2.0: cinematic text-to-video with native audio,
physics, and camera control.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note
that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt used to generate the
video |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `resolution` | `string` | | `720p` | `480p` `720p` `1080p` | Video
resolution - 480p for faster generation, 720p for balance, 1080p for
highest quality. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end
user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3`
`1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9
for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for
ultrawide cinematic, or auto to let the model decide. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
synchronized audio for the video, including sound effects, ambient
sounds, and lip-synced speech. The cost of video generation is the same
regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-image` — Seedance 2.0 Image-to-Video (ByteDance) ·
`image-to-video`
ByteDance Seedance 2.0: animate images with cinematic quality and
synchronized audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note
that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the
desired motion and action for the video. |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `image_url` | `string` | ✓ | – | – | The URL of the starting frame
image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
| `resolution` | `string` | | `720p` | `480p` `720p` `1080p` | Video
resolution - 480p for faster generation, 720p for balance, 1080p for
highest quality. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end
user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3`
`1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9
for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for
ultrawide cinematic, or auto to infer from the input image. |
| `end_image_url` | `string` | | – | – | The URL of the image to use as
the last frame of the video. When provided, the generated video will
transition from the starting image to this ending image. Supported
formats: JPEG, PNG, WebP. Max 30 MB. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
synchronized audio for the video, including sound effects, ambient
sounds, and lip-synced speech. The cost of video generation is the same
regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-image",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-ref` — Seedance 2.0 Reference-to-Video (ByteDance) ·
`reference-to-video`
ByteDance Seedance 2.0: generate video from reference images, videos,
and audio clips.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note
that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt used to generate the
video. |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `audio_urls` | `array` | | – | – | Reference audio to guide video
generation. Refer to them in the prompt as @Audio1, @Audio2, etc.
Supported formats: MP3, WAV. Up to 3 files, combined duration must not
exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one
reference image or video is required. |
| `image_urls` | `array` | | – | – | Reference images to guide video
generation. Refer to them in the prompt as @Image1, @Image2, etc.
Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images.
Total files across all modalities must not exceed 12. |
| `resolution` | `string` | | `720p` | `480p` `720p` `1080p` | Video
resolution - 480p for faster generation, 720p for balance, 1080p for
highest quality. |
| `video_urls` | `array` | | – | – | Reference videos to guide video
generation. Refer to them in the prompt as @Video1, @Video2, etc.
Supported formats: MP4, MOV. Up to 3 videos, combined duration must be
between 2 and 15 seconds, total size under 50 MB. Each video must be
between ~480p (640x640) and ~720p (834x1112) in resolution. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end
user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3`
`1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9
for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for
ultrawide cinematic, or auto to let the model decide. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
synchronized audio for the video, including sound effects, ambient
sounds, and lip-synced speech. The cost of video generation is the same
regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-ref",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"image_urls": [
"https://example.com/sample-image.jpg"
],
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-fast` — Seedance 2.0 Fast (ByteDance) ·
`text-to-video`
ByteDance Seedance 2.0 fast tier: lower-latency text-to-video with
native audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note
that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt used to generate the
video |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `resolution` | `string` | | `720p` | `480p` `720p` | Video resolution
- 480p for faster generation, 720p for balance. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end
user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3`
`1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9
for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for
ultrawide cinematic, or auto to let the model decide. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
synchronized audio for the video, including sound effects, ambient
sounds, and lip-synced speech. The cost of video generation is the same
regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-fast",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-fast-image` — Seedance 2.0 Fast Image-to-Video
(ByteDance) · `image-to-video`
ByteDance Seedance 2.0 fast tier: lower-latency image-to-video with
synchronized audio.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note
that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt describing the
desired motion and action for the video. |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `image_url` | `string` | ✓ | – | – | The URL of the starting frame
image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
| `resolution` | `string` | | `720p` | `480p` `720p` | Video resolution
- 480p for faster generation, 720p for balance. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end
user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3`
`1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9
for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for
ultrawide cinematic, or auto to infer from the input image. |
| `end_image_url` | `string` | | – | – | The URL of the image to use as
the last frame of the video. When provided, the generated video will
transition from the starting image to this ending image. Supported
formats: JPEG, PNG, WebP. Max 30 MB. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
synchronized audio for the video, including sound effects, ambient
sounds, and lip-synced speech. The cost of video generation is the same
regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-fast-image",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"image_url": "https://example.com/sample-image.jpg",
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
### `seedance-2.0-fast-ref` — Seedance 2.0 Fast Reference-to-Video
(ByteDance) · `reference-to-video`
ByteDance Seedance 2.0 fast tier: reference-to-video with lower latency
and cost.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
| `seed` | `integer` | | – | – | Random seed for reproducibility. Note
that results may still vary slightly even with the same seed. |
| `prompt` | `string` | ✓ | – | – | The text prompt used to generate the
video. |
| `duration` | `string` | | `4` | `4` `5` `6` `7` `8` `9` `10` `11`
`12` `13` `14` `15` | Duration of the video in seconds (4-15). |
| `audio_urls` | `array` | | – | – | Reference audio to guide video
generation. Refer to them in the prompt as @Audio1, @Audio2, etc.
Supported formats: MP3, WAV. Up to 3 files, combined duration must not
exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one
reference image or video is required. |
| `image_urls` | `array` | | – | – | Reference images to guide video
generation. Refer to them in the prompt as @Image1, @Image2, etc.
Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images.
Total files across all modalities must not exceed 12. |
| `resolution` | `string` | | `720p` | `480p` `720p` | Video resolution
- 480p for faster generation, 720p for balance. |
| `video_urls` | `array` | | – | – | Reference videos to guide video
generation. Refer to them in the prompt as @Video1, @Video2, etc.
Supported formats: MP4, MOV. Up to 3 videos, combined duration must be
between 2 and 15 seconds, total size under 50 MB. Each video must be
between ~480p (640x640) and ~720p (834x1112) in resolution. |
| `end_user_id` | `string` | | – | – | The unique user ID of the end
user. |
| `aspect_ratio` | `string` | | `auto` | `auto` `21:9` `16:9` `4:3`
`1:1` `3:4` `9:16` | The aspect ratio of the generated video. Use 16:9
for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for
ultrawide cinematic, or auto to let the model decide. |
| `generate_audio` | `boolean` | | `true` | – | Whether to generate
synchronized audio for the video, including sound effects, ambient
sounds, and lip-synced speech. The cost of video generation is the same
regardless of whether audio is generated or not. |
Example request body
```json
{
"model": "seedance-2.0-fast-ref",
"input": {
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": "4",
"image_urls": [
"https://example.com/sample-image.jpg"
],
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": true
}
}
```
---
operationId: HubVideoPublicController_submitVideo
parameters: []
requestBody:
required: true
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/Veo31Request'
- $ref: '#/components/schemas/Veo31ImageRequest'
- $ref: '#/components/schemas/Veo31RefRequest'
- $ref: '#/components/schemas/Veo31FirstLastRequest'
- $ref: '#/components/schemas/Veo31FastRequest'
- $ref: '#/components/schemas/Veo31FastImageRequest'
- $ref: '#/components/schemas/Veo31FastRefRequest'
- $ref: '#/components/schemas/Veo31LiteRequest'
- $ref: '#/components/schemas/Veo31LiteImageRequest'
- $ref: '#/components/schemas/Veo3Request'
- $ref: '#/components/schemas/Veo3ImageRequest'
- $ref: '#/components/schemas/KlingV3StandardRequest'
- $ref: '#/components/schemas/KlingV3StandardImageRequest'
- $ref: '#/components/schemas/KlingV3ProRequest'
- $ref: '#/components/schemas/KlingV3ProImageRequest'
- $ref: '#/components/schemas/Wan27Request'
- $ref: '#/components/schemas/Wan27ImageRequest'
- $ref: '#/components/schemas/Wan27RefRequest'
- $ref: '#/components/schemas/Wan27EditRequest'
- $ref: '#/components/schemas/Seedance20Request'
- $ref: '#/components/schemas/Seedance20ImageRequest'
- $ref: '#/components/schemas/Seedance20RefRequest'
- $ref: '#/components/schemas/Seedance20FastRequest'
- $ref: '#/components/schemas/Seedance20FastImageRequest'
- $ref: '#/components/schemas/Seedance20FastRefRequest'
discriminator:
propertyName: model
mapping:
veo-3.1:
$ref: '#/components/schemas/Veo31Request'
veo-3.1-image:
$ref: '#/components/schemas/Veo31ImageRequest'
veo-3.1-ref:
$ref: '#/components/schemas/Veo31RefRequest'
veo-3.1-first-last:
$ref: '#/components/schemas/Veo31FirstLastRequest'
veo-3.1-fast:
$ref: '#/components/schemas/Veo31FastRequest'
veo-3.1-fast-image:
$ref: '#/components/schemas/Veo31FastImageRequest'
veo-3.1-fast-ref:
$ref: '#/components/schemas/Veo31FastRefRequest'
veo-3.1-lite:
$ref: '#/components/schemas/Veo31LiteRequest'
veo-3.1-lite-image:
$ref: '#/components/schemas/Veo31LiteImageRequest'
veo-3:
$ref: '#/components/schemas/Veo3Request'
veo-3-image:
$ref: '#/components/schemas/Veo3ImageRequest'
kling-v3-standard:
$ref: '#/components/schemas/KlingV3StandardRequest'
kling-v3-standard-image:
$ref: '#/components/schemas/KlingV3StandardImageRequest'
kling-v3-pro:
$ref: '#/components/schemas/KlingV3ProRequest'
kling-v3-pro-image:
$ref: '#/components/schemas/KlingV3ProImageRequest'
wan-2.7:
$ref: '#/components/schemas/Wan27Request'
wan-2.7-image:
$ref: '#/components/schemas/Wan27ImageRequest'
wan-2.7-ref:
$ref: '#/components/schemas/Wan27RefRequest'
wan-2.7-edit:
$ref: '#/components/schemas/Wan27EditRequest'
seedance-2.0:
$ref: '#/components/schemas/Seedance20Request'
seedance-2.0-image:
$ref: '#/components/schemas/Seedance20ImageRequest'
seedance-2.0-ref:
$ref: '#/components/schemas/Seedance20RefRequest'
seedance-2.0-fast:
$ref: '#/components/schemas/Seedance20FastRequest'
seedance-2.0-fast-image:
$ref: '#/components/schemas/Seedance20FastImageRequest'
seedance-2.0-fast-ref:
$ref: '#/components/schemas/Seedance20FastRefRequest'
responses:
'200':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/SubmitResponseDto'
security:
- bearerAuth: []
components:
schemas:
Veo31Request:
type: object
title: Veo 3.1 (Google) [text-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3.1
description: 'Fixed value: `"veo-3.1"`'
input:
$ref: '#/components/schemas/Veo31Input'
example:
model: veo-3.1
input:
prompt: >-
Two person street interview in New York City.
Sample Dialogue:
Host: "Did you hear the news?"
Person: "Yes! Veo 3.1 is now available online. If you want to see
it, go check it out!"
auto_fix: true
duration: 8s
resolution: 720p
aspect_ratio: '16:9'
generate_audio: true
safety_tolerance: '4'
Veo31ImageRequest:
type: object
title: Veo 3.1 Image-to-Video (Google) [image-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3.1-image
description: 'Fixed value: `"veo-3.1-image"`'
input:
$ref: '#/components/schemas/Veo31ImageInput'
example:
model: veo-3.1-image
input:
prompt: >-
A monkey and polar bear host a casual podcast about AI inference,
bringing their unique perspectives from different environments
(tropical vs. arctic) to discuss how AI systems make decisions and
process information.
Sample Dialogue:
Monkey (Banana): "Welcome back to Bananas & Ice! I am Banana"
Polar Bear (Ice): "And I'm Ice!"
duration: 8s
image_url: https://example.com/sample-image.jpg
resolution: 720p
aspect_ratio: auto
generate_audio: true
safety_tolerance: '4'
Veo31RefRequest:
type: object
title: Veo 3.1 Multi-Ref (Google) [reference-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3.1-ref
description: 'Fixed value: `"veo-3.1-ref"`'
input:
$ref: '#/components/schemas/Veo31RefInput'
example:
model: veo-3.1-ref
input:
prompt: >-
A chimpanzee wearing overalls frolics in the grassy field, gently
playing with the butterflies. In the background, a circus tent and
carousel beckon.
duration: 8s
image_urls:
- https://example.com/sample-image.jpg
- https://example.com/sample-image-2.jpg
- https://example.com/sample-image-3.jpg
resolution: 720p
aspect_ratio: '16:9'
generate_audio: true
safety_tolerance: '4'
Veo31FirstLastRequest:
type: object
title: Veo 3.1 First-Last Frame (Google) [first-last-frame-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3.1-first-last
description: 'Fixed value: `"veo-3.1-first-last"`'
input:
$ref: '#/components/schemas/Veo31FirstLastInput'
example:
model: veo-3.1-first-last
input:
prompt: >-
A woman looks into the camera, breathes in, then exclaims
energetically, "have you guys checked out this AI video generation?
It's incredible!"
duration: 8s
resolution: 720p
aspect_ratio: auto
generate_audio: true
last_frame_url: https://example.com/sample-image-2.jpg
first_frame_url: https://example.com/sample-image.jpg
safety_tolerance: '4'
Veo31FastRequest:
type: object
title: Veo 3.1 Fast (Google) [text-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3.1-fast
description: 'Fixed value: `"veo-3.1-fast"`'
input:
$ref: '#/components/schemas/Veo31FastInput'
example:
model: veo-3.1-fast
input:
prompt: >-
Two person street interview in New York City.
Sample Dialogue:
Host: "Did you hear the news?"
Person: "Yes! Veo 3.1 is now available online. If you want to see
it, go check it out!"
auto_fix: true
duration: 8s
resolution: 720p
aspect_ratio: '16:9'
generate_audio: true
safety_tolerance: '4'
Veo31FastImageRequest:
type: object
title: Veo 3.1 Fast Image-to-Video (Google) [image-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3.1-fast-image
description: 'Fixed value: `"veo-3.1-fast-image"`'
input:
$ref: '#/components/schemas/Veo31FastImageInput'
example:
model: veo-3.1-fast-image
input:
prompt: >-
A monkey and polar bear host a casual podcast about AI inference,
bringing their unique perspectives from different environments
(tropical vs. arctic) to discuss how AI systems make decisions and
process information.
Sample Dialogue:
Monkey (Banana): "Welcome back to Bananas & Ice! I am Banana"
Polar Bear (Ice): "And I'm Ice!"
duration: 8s
image_url: https://example.com/sample-image.jpg
resolution: 720p
aspect_ratio: auto
generate_audio: true
safety_tolerance: '4'
Veo31FastRefRequest:
type: object
title: Veo 3.1 Fast Multi-Ref (Google) [reference-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3.1-fast-ref
description: 'Fixed value: `"veo-3.1-fast-ref"`'
input:
$ref: '#/components/schemas/Veo31FastRefInput'
example:
model: veo-3.1-fast-ref
input:
prompt: >-
A chimpanzee wearing overalls frolics in the grassy field, gently
playing with the butterflies. In the background, a circus tent and
carousel beckon.
duration: 8s
image_urls:
- https://example.com/sample-image.jpg
- https://example.com/sample-image-2.jpg
- https://example.com/sample-image-3.jpg
resolution: 720p
aspect_ratio: '16:9'
generate_audio: true
safety_tolerance: '4'
Veo31LiteRequest:
type: object
title: Veo 3.1 Lite (Google) [text-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3.1-lite
description: 'Fixed value: `"veo-3.1-lite"`'
input:
$ref: '#/components/schemas/Veo31LiteInput'
example:
model: veo-3.1-lite
input:
prompt: >-
A massive blue whale glides through crystal-clear deep ocean water,
sunlight rays piercing through the surface above, bioluminescent
plankton scattered around, cinematic slow motion
auto_fix: true
duration: 8s
resolution: 720p
aspect_ratio: '16:9'
generate_audio: true
safety_tolerance: '4'
Veo31LiteImageRequest:
type: object
title: Veo 3.1 Lite Image-to-Video (Google) [image-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3.1-lite-image
description: 'Fixed value: `"veo-3.1-lite-image"`'
input:
$ref: '#/components/schemas/Veo31LiteImageInput'
example:
model: veo-3.1-lite-image
input:
prompt: >-
A massive blue whale glides through crystal-clear deep ocean water,
sunlight rays piercing through the surface above, bioluminescent
plankton scattered around, cinematic slow motion
duration: 8s
image_url: https://example.com/sample-image.jpg
resolution: 720p
aspect_ratio: auto
generate_audio: true
safety_tolerance: '4'
Veo3Request:
type: object
title: Veo 3 (Google) [text-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3
description: 'Fixed value: `"veo-3"`'
input:
$ref: '#/components/schemas/Veo3Input'
example:
model: veo-3
input:
prompt: >-
A casual street interview on a busy New York City sidewalk in the
afternoon. The interviewer holds a plain, unbranded microphone and
asks: Have you seen Google's new Veo3 model It is a super good
model. Person replies: Yeah I saw it, it's already available now.
It's crazy good.
auto_fix: true
duration: 8s
resolution: 720p
aspect_ratio: '16:9'
generate_audio: true
safety_tolerance: '4'
Veo3ImageRequest:
type: object
title: Veo 3 Image-to-Video (Google) [image-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- veo-3-image
description: 'Fixed value: `"veo-3-image"`'
input:
$ref: '#/components/schemas/Veo3ImageInput'
example:
model: veo-3-image
input:
prompt: >-
A woman looks into the camera, breathes in, then exclaims
energetically, "have you guys checked out this AI video generation?
It's incredible!"
duration: 8s
image_url: https://example.com/sample-image.jpg
resolution: 720p
aspect_ratio: auto
generate_audio: true
safety_tolerance: '4'
KlingV3StandardRequest:
type: object
title: Kling v3 Standard (Kuaishou) [text-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- kling-v3-standard
description: 'Fixed value: `"kling-v3-standard"`'
input:
$ref: '#/components/schemas/KlingV3StandardInput'
example:
model: kling-v3-standard
input:
prompt: >-
Cinematic drone shot flying through ancient stone ruins covered in
moss and vines at golden hour. Camera starts low, rises through
crumbling archways, revealing a vast misty valley beyond. Volumetric
light rays pierce through gaps in the stone. Epic scale,
photorealistic, 8K quality.
duration: '5'
cfg_scale: 0.5
shot_type: customize
aspect_ratio: '16:9'
multi_prompt: null
generate_audio: true
negative_prompt: blur, distort, and low quality
KlingV3StandardImageRequest:
type: object
title: Kling v3 Standard Image-to-Video (Kuaishou) [image-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- kling-v3-standard-image
description: 'Fixed value: `"kling-v3-standard-image"`'
input:
$ref: '#/components/schemas/KlingV3StandardImageInput'
example:
model: kling-v3-standard-image
input:
prompt: >-
Camera slowly orbits around the vase. Soft light shifts across the
ceramic surface. The pampas grass sways gently. Shadows move
elegantly. Smooth continuous motion, premium feel.
duration: '12'
cfg_scale: 0.5
shot_type: customize
multi_prompt: null
generate_audio: true
negative_prompt: blur, distort, and low quality
start_image_url: https://example.com/sample-image.jpg
KlingV3ProRequest:
type: object
title: Kling v3 Pro (Kuaishou) [text-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- kling-v3-pro
description: 'Fixed value: `"kling-v3-pro"`'
input:
$ref: '#/components/schemas/KlingV3ProInput'
example:
model: kling-v3-pro
input:
prompt: >-
Close-up of glowing fireflies dancing in a dark forest at twilight.
Soft bioluminescent particles float through the air. Shallow depth
of field, bokeh lights in background. Magical atmosphere, gentle
movement.
duration: '5'
cfg_scale: 0.5
shot_type: customize
aspect_ratio: '16:9'
multi_prompt: null
generate_audio: true
negative_prompt: blur, distort, and low quality
KlingV3ProImageRequest:
type: object
title: Kling v3 Pro Image-to-Video (Kuaishou) [image-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- kling-v3-pro-image
description: 'Fixed value: `"kling-v3-pro-image"`'
input:
$ref: '#/components/schemas/KlingV3ProImageInput'
example:
model: kling-v3-pro-image
input:
prompt: >-
The craftsman slowly examines the bowl, turning it gently in his
weathered hands. His eyes reflect years of wisdom. Subtle smile
forms on his face. Dust particles drift in warm light. Breathing
motion, blinking eyes.
duration: '12'
cfg_scale: 0.5
shot_type: customize
multi_prompt: null
generate_audio: true
negative_prompt: blur, distort, and low quality
start_image_url: https://example.com/sample-image.jpg
Wan27Request:
type: object
title: WAN 2.7 (Alibaba) [text-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- wan-2.7
description: 'Fixed value: `"wan-2.7"`'
input:
$ref: '#/components/schemas/Wan27Input'
example:
model: wan-2.7
input:
prompt: >-
A kitten running in a meadow, cinematic lighting, smooth camera
movement.
duration: 5
resolution: 1080p
aspect_ratio: '16:9'
negative_prompt: low resolution, errors, worst quality, low quality
enable_safety_checker: true
enable_prompt_expansion: true
Wan27ImageRequest:
type: object
title: WAN 2.7 Image-to-Video (Alibaba) [image-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- wan-2.7-image
description: 'Fixed value: `"wan-2.7-image"`'
input:
$ref: '#/components/schemas/Wan27ImageInput'
example:
model: wan-2.7-image
input:
prompt: >-
The massive humpback whale glides slowly through the deep blue
water. It turns gracefully, its huge pectoral fin sweeping through
the water like a wing. Sunbeams penetrate from above, illuminating
the whale's textured skin. Small fish scatter. Awe-inspiring scale
and grace.
duration: 5
image_url: https://example.com/sample-image.jpg
resolution: 1080p
negative_prompt: >-
low resolution, errors, worst quality, low quality, incomplete,
extra fingers, bad proportions, blurry, distorted
enable_safety_checker: true
enable_prompt_expansion: true
Wan27RefRequest:
type: object
title: WAN 2.7 Reference-to-Video (Alibaba) [reference-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- wan-2.7-ref
description: 'Fixed value: `"wan-2.7-ref"`'
input:
$ref: '#/components/schemas/Wan27RefInput'
example:
model: wan-2.7-ref
input:
prompt: A person walking through a beautiful garden, cinematic style.
duration: 5
resolution: 1080p
aspect_ratio: '16:9'
negative_prompt: low resolution, errors, worst quality, low quality
enable_safety_checker: true
Wan27EditRequest:
type: object
title: WAN 2.7 Edit Video (Alibaba) [video-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- wan-2.7-edit
description: 'Fixed value: `"wan-2.7-edit"`'
input:
$ref: '#/components/schemas/Wan27EditInput'
example:
model: wan-2.7-edit
input:
prompt: >-
Transform the entire scene into a beautiful watercolor painting
style. Soft brushstrokes, flowing paint washes, visible paper
texture. Colors should bleed and blend naturally like wet watercolor
on paper.
video_url: https://example.com/sample-video.mp4
resolution: 1080p
audio_setting: auto
enable_safety_checker: true
Seedance20Request:
type: object
title: Seedance 2.0 (ByteDance) [text-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- seedance-2.0
description: 'Fixed value: `"seedance-2.0"`'
input:
$ref: '#/components/schemas/Seedance20Input'
example:
model: seedance-2.0
input:
prompt: >-
An octopus finds a football in the ocean and excitedly calls its
octopus friends to come and play. Cut scene to an octopus football
game under the sea.
duration: '4'
resolution: 720p
aspect_ratio: auto
generate_audio: true
Seedance20ImageRequest:
type: object
title: Seedance 2.0 Image-to-Video (ByteDance) [image-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- seedance-2.0-image
description: 'Fixed value: `"seedance-2.0-image"`'
input:
$ref: '#/components/schemas/Seedance20ImageInput'
example:
model: seedance-2.0-image
input:
prompt: >-
An octopus finds a football in the ocean and excitedly calls its
octopus friends to come and play. Cut scene to an octopus football
game under the sea.
duration: '4'
image_url: https://example.com/sample-image.jpg
resolution: 720p
aspect_ratio: auto
generate_audio: true
Seedance20RefRequest:
type: object
title: Seedance 2.0 Reference-to-Video (ByteDance) [reference-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- seedance-2.0-ref
description: 'Fixed value: `"seedance-2.0-ref"`'
input:
$ref: '#/components/schemas/Seedance20RefInput'
example:
model: seedance-2.0-ref
input:
prompt: >-
An octopus finds a football in the ocean and excitedly calls its
octopus friends to come and play. Cut scene to an octopus football
game under the sea.
duration: '4'
image_urls:
- https://example.com/sample-image.jpg
resolution: 720p
aspect_ratio: auto
generate_audio: true
Seedance20FastRequest:
type: object
title: Seedance 2.0 Fast (ByteDance) [text-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- seedance-2.0-fast
description: 'Fixed value: `"seedance-2.0-fast"`'
input:
$ref: '#/components/schemas/Seedance20FastInput'
example:
model: seedance-2.0-fast
input:
prompt: >-
An octopus finds a football in the ocean and excitedly calls its
octopus friends to come and play. Cut scene to an octopus football
game under the sea.
duration: '4'
resolution: 720p
aspect_ratio: auto
generate_audio: true
Seedance20FastImageRequest:
type: object
title: Seedance 2.0 Fast Image-to-Video (ByteDance) [image-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- seedance-2.0-fast-image
description: 'Fixed value: `"seedance-2.0-fast-image"`'
input:
$ref: '#/components/schemas/Seedance20FastImageInput'
example:
model: seedance-2.0-fast-image
input:
prompt: >-
An octopus finds a football in the ocean and excitedly calls its
octopus friends to come and play. Cut scene to an octopus football
game under the sea.
duration: '4'
image_url: https://example.com/sample-image.jpg
resolution: 720p
aspect_ratio: auto
generate_audio: true
Seedance20FastRefRequest:
type: object
title: Seedance 2.0 Fast Reference-to-Video (ByteDance) [reference-to-video]
required:
- model
- input
properties:
model:
type: string
enum:
- seedance-2.0-fast-ref
description: 'Fixed value: `"seedance-2.0-fast-ref"`'
input:
$ref: '#/components/schemas/Seedance20FastRefInput'
example:
model: seedance-2.0-fast-ref
input:
prompt: >-
An octopus finds a football in the ocean and excitedly calls its
octopus friends to come and play. Cut scene to an octopus football
game under the sea.
duration: '4'
image_urls:
- https://example.com/sample-image.jpg
resolution: 720p
aspect_ratio: auto
generate_audio: true
SubmitResponseDto:
type: object
properties:
task_id:
type: string
description: Unique task ID — use this to poll GET /hub/v1/tasks/:task_id
example: hub-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
status:
type: string
description: Task status at creation time (usually `pending`)
example: pending
capability:
type: string
description: 'Capability: `image` | `video` | `audio` | `transcribe`'
example: video
model:
type: string
description: Model ID
example: veo-3.1-fast
vendor:
type: string
description: Model vendor
example: Google
mode:
type: string
description: Generation mode (e.g. `text-to-video`, `image-to-image`)
example: text-to-video
created_at:
type: string
description: ISO 8601 creation timestamp
example: '2026-05-18T09:00:00.000Z'
required:
- task_id
- status
- capability
- model
- vendor
- mode
- created_at
Veo31Input:
type: object
title: Veo 3.1 — input
description: Google Veo 3.1 text-to-video with optional native audio.
properties:
seed:
type: integer
description: The seed for the random number generator.
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
default: true
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
- 4k
default: 720p
aspect_ratio:
type: string
description: Aspect ratio of the generated video
enum:
- '16:9'
- '9:16'
default: '16:9'
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
negative_prompt:
type: string
description: A negative prompt to guide the video generation.
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
Veo31ImageInput:
type: object
title: Veo 3.1 Image-to-Video — input
description: 'Veo 3.1: animate a single reference image.'
properties:
seed:
type: integer
description: The seed for the random number generator.
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
image_url:
type: string
description: >-
URL of the input image to animate. Should be 720p or higher
resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9
or 9:16 aspect ratio, it will be cropped to fit.
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
- 4k
default: 720p
aspect_ratio:
type: string
description: >-
The aspect ratio of the generated video. Only 16:9 and 9:16 are
supported.
enum:
- auto
- '16:9'
- '9:16'
default: auto
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
negative_prompt:
type: string
description: A negative prompt to guide the video generation.
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
- image_url
Veo31RefInput:
type: object
title: Veo 3.1 Multi-Ref — input
description: >-
Veo 3.1: generate video from reference images for consistent subject
appearance.
properties:
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
image_urls:
type: array
description: >-
URLs of the reference images to use for consistent subject
appearance
items:
type: string
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
- 4k
default: 720p
aspect_ratio:
type: string
description: The aspect ratio of the generated video.
enum:
- '16:9'
- '9:16'
default: '16:9'
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
- image_urls
Veo31FirstLastInput:
type: object
title: Veo 3.1 First-Last Frame — input
description: >-
Veo 3.1: generate a transition video between a start frame and an end
frame.
properties:
seed:
type: integer
description: The seed for the random number generator.
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
- 4k
default: 720p
aspect_ratio:
type: string
description: The aspect ratio of the generated video.
enum:
- auto
- '16:9'
- '9:16'
default: auto
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
last_frame_url:
type: string
description: URL of the last frame of the video
first_frame_url:
type: string
description: URL of the first frame of the video
negative_prompt:
type: string
description: A negative prompt to guide the video generation.
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
- last_frame_url
- first_frame_url
Veo31FastInput:
type: object
title: Veo 3.1 Fast — input
description: 'Veo 3.1 Fast: lower-latency text-to-video at reduced cost.'
properties:
seed:
type: integer
description: The seed for the random number generator.
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
default: true
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
- 4k
default: 720p
aspect_ratio:
type: string
description: Aspect ratio of the generated video
enum:
- '16:9'
- '9:16'
default: '16:9'
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
negative_prompt:
type: string
description: A negative prompt to guide the video generation.
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
Veo31FastImageInput:
type: object
title: Veo 3.1 Fast Image-to-Video — input
description: 'Veo 3.1 Fast: animate a reference image at lower cost.'
properties:
seed:
type: integer
description: The seed for the random number generator.
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
image_url:
type: string
description: >-
URL of the input image to animate. Should be 720p or higher
resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9
or 9:16 aspect ratio, it will be cropped to fit.
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
- 4k
default: 720p
aspect_ratio:
type: string
description: >-
The aspect ratio of the generated video. Only 16:9 and 9:16 are
supported.
enum:
- auto
- '16:9'
- '9:16'
default: auto
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
negative_prompt:
type: string
description: A negative prompt to guide the video generation.
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
- image_url
Veo31FastRefInput:
type: object
title: Veo 3.1 Fast Multi-Ref — input
description: 'Veo 3.1 Fast: multi-reference video at lower cost.'
properties:
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
image_urls:
type: array
description: >-
URLs of the reference images to use for consistent subject
appearance
items:
type: string
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
- 4k
default: 720p
aspect_ratio:
type: string
description: The aspect ratio of the generated video.
enum:
- '16:9'
- '9:16'
default: '16:9'
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
- image_urls
Veo31LiteInput:
type: object
title: Veo 3.1 Lite — input
description: 'Veo 3.1 Lite: lowest cost text-to-video (720p/1080p only).'
properties:
seed:
type: integer
description: The seed for the random number generator.
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
default: true
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
default: 720p
aspect_ratio:
type: string
description: Aspect ratio of the generated video
enum:
- '16:9'
- '9:16'
default: '16:9'
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
negative_prompt:
type: string
description: A negative prompt to guide the video generation.
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
Veo31LiteImageInput:
type: object
title: Veo 3.1 Lite Image-to-Video — input
description: 'Veo 3.1 Lite: animate a reference image at lowest cost.'
properties:
seed:
type: integer
description: The seed for the random number generator.
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
image_url:
type: string
description: >-
URL of the input image to animate. Should be 720p or higher
resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9
or 9:16 aspect ratio, it will be cropped to fit.
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
default: 720p
aspect_ratio:
type: string
description: >-
The aspect ratio of the generated video. Only 16:9 and 9:16 are
supported.
enum:
- auto
- '16:9'
- '9:16'
default: auto
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
negative_prompt:
type: string
description: A negative prompt to guide the video generation.
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
- image_url
Veo3Input:
type: object
title: Veo 3 — input
description: Google Veo 3 text-to-video with native audio.
properties:
seed:
type: integer
description: The seed for the random number generator.
prompt:
type: string
description: The text prompt describing the video you want to generate
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
default: true
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
default: 720p
aspect_ratio:
type: string
description: The aspect ratio of the generated video.
enum:
- '16:9'
- '9:16'
default: '16:9'
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
negative_prompt:
type: string
description: A negative prompt to guide the video generation.
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
Veo3ImageInput:
type: object
title: Veo 3 Image-to-Video — input
description: 'Google Veo 3: animate a single reference image.'
properties:
seed:
type: integer
description: The seed for the random number generator.
prompt:
type: string
description: The text prompt describing how the image should be animated
auto_fix:
type: boolean
description: >-
Whether to automatically attempt to fix prompts that fail content
policy or other validation checks by rewriting them.
duration:
type: string
description: The duration of the generated video.
enum:
- 4s
- 6s
- 8s
default: 8s
image_url:
type: string
description: >-
URL of the input image to animate. Should be 720p or higher
resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9
or 9:16 aspect ratio, it will be cropped to fit.
resolution:
type: string
description: The resolution of the generated video.
enum:
- 720p
- 1080p
default: 720p
aspect_ratio:
type: string
description: The aspect ratio of the generated video.
enum:
- auto
- '16:9'
- '9:16'
default: auto
generate_audio:
type: boolean
description: Whether to generate audio for the video.
default: true
negative_prompt:
type: string
description: A negative prompt to guide the video generation.
safety_tolerance:
type: string
description: >-
The safety tolerance level for content moderation. 1 is the most
strict (blocks most content), 6 is the least strict. Note: API-only
parameter.
enum:
- '1'
- '2'
- '3'
- '4'
- '5'
- '6'
default: '4'
required:
- prompt
- image_url
KlingV3StandardInput:
type: object
title: Kling v3 Standard — input
description: Kling v3 Standard text-to-video with optional native audio.
properties:
prompt:
type: string
description: >-
Text prompt for video generation. Either prompt or multi_prompt must
be provided, but not both.
duration:
type: string
description: The duration of the generated video in seconds
enum:
- '3'
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '5'
cfg_scale:
type: number
description: >-
The CFG (Classifier Free Guidance) scale is a measure of how close
you want the model to stick to your prompt.
default: 0.5
shot_type:
type: string
description: >-
The type of multi-shot video generation. 'intelligent' lets the
model automatically determine shot structure.
enum:
- customize
- intelligent
default: customize
aspect_ratio:
type: string
description: The aspect ratio of the generated video frame
enum:
- '16:9'
- '9:16'
- '1:1'
default: '16:9'
multi_prompt:
type: array
description: >-
List of prompts for multi-shot video generation. If provided,
overrides the single prompt and divides the video into multiple
shots with specified prompts and durations.
items:
type: object
generate_audio:
type: boolean
description: >-
Whether to generate native audio for the video. Supports Chinese and
English voice output. Other languages are automatically translated
to English. For English speech, use lowercase letters; for acronyms
or proper nouns, use uppercase.
default: true
negative_prompt:
type: string
default: blur, distort, and low quality
KlingV3StandardImageInput:
type: object
title: Kling v3 Standard Image-to-Video — input
description: Kling v3 Standard image-to-video (3-15 seconds).
properties:
prompt:
type: string
description: >-
Text prompt for video generation. Either prompt or multi_prompt must
be provided, but not both.
duration:
type: string
description: The duration of the generated video in seconds
enum:
- '3'
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '5'
elements:
type: array
description: >-
Elements (characters/objects) to include in the video. Each element
can either be an image set (frontal + reference images) or a video.
Reference in prompt as @Element1, @Element2, etc.
items:
type: object
cfg_scale:
type: number
description: >-
The CFG (Classifier Free Guidance) scale is a measure of how close
you want the model to stick to your prompt.
default: 0.5
shot_type:
type: string
description: >-
The type of multi-shot video generation. 'intelligent' lets the
model automatically determine shot structure.
enum:
- customize
- intelligent
default: customize
multi_prompt:
type: array
description: >-
List of prompts for multi-shot video generation. If provided,
divides the video into multiple shots.
items:
type: object
end_image_url:
type: string
description: URL of the image to be used for the end of the video
generate_audio:
type: boolean
description: >-
Whether to generate native audio for the video. Supports Chinese and
English voice output. Other languages are automatically translated
to English. For English speech, use lowercase letters; for acronyms
or proper nouns, use uppercase.
default: true
negative_prompt:
type: string
default: blur, distort, and low quality
start_image_url:
type: string
description: URL of the image to be used for the video
required:
- start_image_url
KlingV3ProInput:
type: object
title: Kling v3 Pro — input
description: Kling v3 Pro text-to-video with optional native audio.
properties:
prompt:
type: string
description: >-
Text prompt for video generation. Either prompt or multi_prompt must
be provided, but not both.
duration:
type: string
description: The duration of the generated video in seconds
enum:
- '3'
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '5'
cfg_scale:
type: number
description: >-
The CFG (Classifier Free Guidance) scale is a measure of how close
you want the model to stick to your prompt.
default: 0.5
shot_type:
type: string
description: >-
The type of multi-shot video generation. 'intelligent' lets the
model automatically determine shot structure.
enum:
- customize
- intelligent
default: customize
aspect_ratio:
type: string
description: The aspect ratio of the generated video frame
enum:
- '16:9'
- '9:16'
- '1:1'
default: '16:9'
multi_prompt:
type: array
description: >-
List of prompts for multi-shot video generation. If provided,
overrides the single prompt and divides the video into multiple
shots with specified prompts and durations.
items:
type: object
generate_audio:
type: boolean
description: >-
Whether to generate native audio for the video. Supports Chinese and
English voice output. Other languages are automatically translated
to English. For English speech, use lowercase letters; for acronyms
or proper nouns, use uppercase.
default: true
negative_prompt:
type: string
default: blur, distort, and low quality
KlingV3ProImageInput:
type: object
title: Kling v3 Pro Image-to-Video — input
description: Kling v3 Pro image-to-video (3-15 seconds).
properties:
prompt:
type: string
description: >-
Text prompt for video generation. Either prompt or multi_prompt must
be provided, but not both.
duration:
type: string
description: The duration of the generated video in seconds
enum:
- '3'
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '5'
elements:
type: array
description: >-
Elements (characters/objects) to include in the video. Each element
can either be an image set (frontal + reference images) or a video.
Reference in prompt as @Element1, @Element2, etc.
items:
type: object
cfg_scale:
type: number
description: >-
The CFG (Classifier Free Guidance) scale is a measure of how close
you want the model to stick to your prompt.
default: 0.5
shot_type:
type: string
description: >-
The type of multi-shot video generation. 'intelligent' lets the
model automatically determine shot structure.
enum:
- customize
- intelligent
default: customize
multi_prompt:
type: array
description: >-
List of prompts for multi-shot video generation. If provided,
divides the video into multiple shots.
items:
type: object
end_image_url:
type: string
description: URL of the image to be used for the end of the video
generate_audio:
type: boolean
description: >-
Whether to generate native audio for the video. Supports Chinese and
English voice output. Other languages are automatically translated
to English. For English speech, use lowercase letters; for acronyms
or proper nouns, use uppercase.
default: true
negative_prompt:
type: string
default: blur, distort, and low quality
start_image_url:
type: string
description: URL of the image to be used for the video
required:
- start_image_url
Wan27Input:
type: object
title: WAN 2.7 — input
description: >-
WAN 2.7 text-to-video - high quality generation. Default resolution is
1080p.
properties:
seed:
type: integer
description: Random seed for reproducibility (0-2147483647).
prompt:
type: string
description: Text prompt describing the desired video. Max 5000 characters.
duration:
type: integer
description: Output video duration in seconds (2-15).
enum:
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
default: 5
audio_url:
type: string
description: >-
URL of driving audio. Supports WAV and MP3. Duration: 3-30s. Max 15
MB. If not provided, the model auto-generates matching background
music.
resolution:
type: string
description: Output video resolution tier.
enum:
- 720p
- 1080p
default: 1080p
aspect_ratio:
type: string
description: Aspect ratio of the generated video.
enum:
- '16:9'
- '9:16'
- '1:1'
- '4:3'
- '3:4'
default: '16:9'
negative_prompt:
type: string
description: Content to avoid in the video. Max 500 characters.
enable_safety_checker:
type: boolean
description: Enable content moderation for input and output.
default: true
enable_prompt_expansion:
type: boolean
description: Enable intelligent prompt rewriting.
default: true
required:
- prompt
Wan27ImageInput:
type: object
title: WAN 2.7 Image-to-Video — input
description: WAN 2.7 image-to-video (720p/1080p, duration 2-15s).
properties:
seed:
type: integer
description: Random seed for reproducibility (0-2147483647).
prompt:
type: string
description: Text prompt describing the desired video. Max 5000 characters.
duration:
type: integer
description: Output video duration in seconds (2-15).
enum:
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
default: 5
audio_url:
type: string
description: >-
URL of driving audio. Supports WAV and MP3. Duration: 2-30s. Max 15
MB.
image_url:
type: string
description: >-
URL of the first frame image. Formats: JPEG, JPG, PNG, BMP, WEBP.
Max 20 MB.
video_url:
type: string
description: >-
URL of a video clip to continue from. Format: MP4, MOV. Duration:
2-10s. Max 100 MB. Cannot be combined with image_url.
resolution:
type: string
description: Output video resolution tier.
enum:
- 720p
- 1080p
default: 1080p
end_image_url:
type: string
description: >-
URL of the last frame image for first-and-last-frame-to-video. Same
constraints as image_url.
negative_prompt:
type: string
description: Content to avoid in the video. Max 500 characters.
enable_safety_checker:
type: boolean
description: Enable content moderation for input and output.
default: true
enable_prompt_expansion:
type: boolean
description: Enable intelligent prompt rewriting.
default: true
Wan27RefInput:
type: object
title: WAN 2.7 Reference-to-Video — input
description: >-
WAN 2.7 reference-to-video using character/object reference images and
videos (duration 2-10s).
properties:
seed:
type: integer
description: Random seed for reproducibility (0-2147483647).
prompt:
type: string
description: Text prompt describing the desired video. Max 5000 characters.
duration:
type: integer
description: Output video duration in seconds (2-10).
enum:
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
default: 5
resolution:
type: string
description: Output video resolution tier.
enum:
- 720p
- 1080p
default: 1080p
multi_shots:
type: boolean
description: >-
When true, enables intelligent multi-shot segmentation. When false
(default), generates a single continuous shot.
default: false
aspect_ratio:
type: string
description: Aspect ratio of the generated video.
enum:
- '16:9'
- '9:16'
- '1:1'
- '4:3'
- '3:4'
default: '16:9'
negative_prompt:
type: string
description: Content to avoid in the video. Max 500 characters.
reference_image_urls:
type: array
description: >-
Reference image URLs for character/object appearance. Pass multiple
images for multi-subject generation. Max 20 MB each.
items:
type: string
reference_video_urls:
type: array
description: >-
Reference video URLs for character/object appearance and motion.
Pass multiple videos for multi-subject generation. Max 100 MB each.
Note: when video inputs are provided, billing includes the total
input video duration plus the output duration. Your charged credits
will be higher than the output duration alone.
items:
type: string
enable_safety_checker:
type: boolean
description: Enable content moderation for input and output.
default: true
required:
- prompt
Wan27EditInput:
type: object
title: WAN 2.7 Edit Video — input
description: >-
WAN 2.7 video editing: instruction-based editing, reference-image-based
editing and style transfer (input video 2-10s).
properties:
seed:
type: integer
description: Random seed for reproducibility (0-2147483647).
prompt:
type: string
description: >-
Editing instruction or style transfer description. Describe what
changes you want applied to the video.
duration:
type: string
description: >-
Output duration in seconds. '0' means match the input video's
duration. When set to 2-10, the output is truncated to that length
from the start.
enum:
- '0'
- '2'
- '3'
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
default: '0'
video_url:
type: string
description: >-
URL of the input video to edit. Format: MP4, MOV. Duration: 2-10s.
Max 100 MB.
resolution:
type: string
description: Output video resolution tier.
enum:
- 720p
- 1080p
default: 1080p
aspect_ratio:
type: string
description: >-
Aspect ratio of the output video. If not provided, uses the input
video's aspect ratio.
enum:
- '16:9'
- '9:16'
- '1:1'
- '4:3'
- '3:4'
audio_setting:
type: string
description: >-
Audio handling: 'auto' lets the model decide whether to regenerate
audio; 'origin' preserves the original audio from the input video.
enum:
- auto
- origin
default: auto
reference_image_url:
type: string
description: >-
Optional reference image URL for reference-based editing. When
provided, the edit is guided by the visual style or content of this
image.
enable_safety_checker:
type: boolean
description: Enable content moderation for input and output.
default: true
required:
- prompt
- video_url
Seedance20Input:
type: object
title: Seedance 2.0 — input
description: >-
ByteDance Seedance 2.0: cinematic text-to-video with native audio,
physics, and camera control.
properties:
seed:
type: integer
description: >-
Random seed for reproducibility. Note that results may still vary
slightly even with the same seed.
prompt:
type: string
description: The text prompt used to generate the video
duration:
type: string
description: Duration of the video in seconds (4-15).
enum:
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '4'
resolution:
type: string
description: >-
Video resolution - 480p for faster generation, 720p for balance,
1080p for highest quality.
enum:
- 480p
- 720p
- 1080p
default: 720p
end_user_id:
type: string
description: The unique user ID of the end user.
aspect_ratio:
type: string
description: >-
The aspect ratio of the generated video. Use 16:9 for landscape,
9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide
cinematic, or auto to let the model decide.
enum:
- auto
- '21:9'
- '16:9'
- '4:3'
- '1:1'
- '3:4'
- '9:16'
default: auto
generate_audio:
type: boolean
description: >-
Whether to generate synchronized audio for the video, including
sound effects, ambient sounds, and lip-synced speech. The cost of
video generation is the same regardless of whether audio is
generated or not.
default: true
required:
- prompt
Seedance20ImageInput:
type: object
title: Seedance 2.0 Image-to-Video — input
description: >-
ByteDance Seedance 2.0: animate images with cinematic quality and
synchronized audio.
properties:
seed:
type: integer
description: >-
Random seed for reproducibility. Note that results may still vary
slightly even with the same seed.
prompt:
type: string
description: >-
The text prompt describing the desired motion and action for the
video.
duration:
type: string
description: Duration of the video in seconds (4-15).
enum:
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '4'
image_url:
type: string
description: >-
The URL of the starting frame image to animate. Supported formats:
JPEG, PNG, WebP. Max 30 MB.
resolution:
type: string
description: >-
Video resolution - 480p for faster generation, 720p for balance,
1080p for highest quality.
enum:
- 480p
- 720p
- 1080p
default: 720p
end_user_id:
type: string
description: The unique user ID of the end user.
aspect_ratio:
type: string
description: >-
The aspect ratio of the generated video. Use 16:9 for landscape,
9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide
cinematic, or auto to infer from the input image.
enum:
- auto
- '21:9'
- '16:9'
- '4:3'
- '1:1'
- '3:4'
- '9:16'
default: auto
end_image_url:
type: string
description: >-
The URL of the image to use as the last frame of the video. When
provided, the generated video will transition from the starting
image to this ending image. Supported formats: JPEG, PNG, WebP. Max
30 MB.
generate_audio:
type: boolean
description: >-
Whether to generate synchronized audio for the video, including
sound effects, ambient sounds, and lip-synced speech. The cost of
video generation is the same regardless of whether audio is
generated or not.
default: true
required:
- prompt
- image_url
Seedance20RefInput:
type: object
title: Seedance 2.0 Reference-to-Video — input
description: >-
ByteDance Seedance 2.0: generate video from reference images, videos,
and audio clips.
properties:
seed:
type: integer
description: >-
Random seed for reproducibility. Note that results may still vary
slightly even with the same seed.
prompt:
type: string
description: The text prompt used to generate the video.
duration:
type: string
description: Duration of the video in seconds (4-15).
enum:
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '4'
audio_urls:
type: array
description: >-
Reference audio to guide video generation. Refer to them in the
prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to
3 files, combined duration must not exceed 15 seconds. Max 15 MB per
file.If audio is provided, at least one reference image or video is
required.
items:
type: string
image_urls:
type: array
description: >-
Reference images to guide video generation. Refer to them in the
prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP.
Max 30 MB per image. Up to 9 images. Total files across all
modalities must not exceed 12.
items:
type: string
resolution:
type: string
description: >-
Video resolution - 480p for faster generation, 720p for balance,
1080p for highest quality.
enum:
- 480p
- 720p
- 1080p
default: 720p
video_urls:
type: array
description: >-
Reference videos to guide video generation. Refer to them in the
prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to
3 videos, combined duration must be between 2 and 15 seconds, total
size under 50 MB. Each video must be between ~480p (640x640) and
~720p (834x1112) in resolution.
items:
type: string
end_user_id:
type: string
description: The unique user ID of the end user.
aspect_ratio:
type: string
description: >-
The aspect ratio of the generated video. Use 16:9 for landscape,
9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide
cinematic, or auto to let the model decide.
enum:
- auto
- '21:9'
- '16:9'
- '4:3'
- '1:1'
- '3:4'
- '9:16'
default: auto
generate_audio:
type: boolean
description: >-
Whether to generate synchronized audio for the video, including
sound effects, ambient sounds, and lip-synced speech. The cost of
video generation is the same regardless of whether audio is
generated or not.
default: true
required:
- prompt
Seedance20FastInput:
type: object
title: Seedance 2.0 Fast — input
description: >-
ByteDance Seedance 2.0 fast tier: lower-latency text-to-video with
native audio.
properties:
seed:
type: integer
description: >-
Random seed for reproducibility. Note that results may still vary
slightly even with the same seed.
prompt:
type: string
description: The text prompt used to generate the video
duration:
type: string
description: Duration of the video in seconds (4-15).
enum:
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '4'
resolution:
type: string
description: Video resolution - 480p for faster generation, 720p for balance.
enum:
- 480p
- 720p
default: 720p
end_user_id:
type: string
description: The unique user ID of the end user.
aspect_ratio:
type: string
description: >-
The aspect ratio of the generated video. Use 16:9 for landscape,
9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide
cinematic, or auto to let the model decide.
enum:
- auto
- '21:9'
- '16:9'
- '4:3'
- '1:1'
- '3:4'
- '9:16'
default: auto
generate_audio:
type: boolean
description: >-
Whether to generate synchronized audio for the video, including
sound effects, ambient sounds, and lip-synced speech. The cost of
video generation is the same regardless of whether audio is
generated or not.
default: true
required:
- prompt
Seedance20FastImageInput:
type: object
title: Seedance 2.0 Fast Image-to-Video — input
description: >-
ByteDance Seedance 2.0 fast tier: lower-latency image-to-video with
synchronized audio.
properties:
seed:
type: integer
description: >-
Random seed for reproducibility. Note that results may still vary
slightly even with the same seed.
prompt:
type: string
description: >-
The text prompt describing the desired motion and action for the
video.
duration:
type: string
description: Duration of the video in seconds (4-15).
enum:
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '4'
image_url:
type: string
description: >-
The URL of the starting frame image to animate. Supported formats:
JPEG, PNG, WebP. Max 30 MB.
resolution:
type: string
description: Video resolution - 480p for faster generation, 720p for balance.
enum:
- 480p
- 720p
default: 720p
end_user_id:
type: string
description: The unique user ID of the end user.
aspect_ratio:
type: string
description: >-
The aspect ratio of the generated video. Use 16:9 for landscape,
9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide
cinematic, or auto to infer from the input image.
enum:
- auto
- '21:9'
- '16:9'
- '4:3'
- '1:1'
- '3:4'
- '9:16'
default: auto
end_image_url:
type: string
description: >-
The URL of the image to use as the last frame of the video. When
provided, the generated video will transition from the starting
image to this ending image. Supported formats: JPEG, PNG, WebP. Max
30 MB.
generate_audio:
type: boolean
description: >-
Whether to generate synchronized audio for the video, including
sound effects, ambient sounds, and lip-synced speech. The cost of
video generation is the same regardless of whether audio is
generated or not.
default: true
required:
- prompt
- image_url
Seedance20FastRefInput:
type: object
title: Seedance 2.0 Fast Reference-to-Video — input
description: >-
ByteDance Seedance 2.0 fast tier: reference-to-video with lower latency
and cost.
properties:
seed:
type: integer
description: >-
Random seed for reproducibility. Note that results may still vary
slightly even with the same seed.
prompt:
type: string
description: The text prompt used to generate the video.
duration:
type: string
description: Duration of the video in seconds (4-15).
enum:
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
default: '4'
audio_urls:
type: array
description: >-
Reference audio to guide video generation. Refer to them in the
prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to
3 files, combined duration must not exceed 15 seconds. Max 15 MB per
file.If audio is provided, at least one reference image or video is
required.
items:
type: string
image_urls:
type: array
description: >-
Reference images to guide video generation. Refer to them in the
prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP.
Max 30 MB per image. Up to 9 images. Total files across all
modalities must not exceed 12.
items:
type: string
resolution:
type: string
description: Video resolution - 480p for faster generation, 720p for balance.
enum:
- 480p
- 720p
default: 720p
video_urls:
type: array
description: >-
Reference videos to guide video generation. Refer to them in the
prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to
3 videos, combined duration must be between 2 and 15 seconds, total
size under 50 MB. Each video must be between ~480p (640x640) and
~720p (834x1112) in resolution.
items:
type: string
end_user_id:
type: string
description: The unique user ID of the end user.
aspect_ratio:
type: string
description: >-
The aspect ratio of the generated video. Use 16:9 for landscape,
9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide
cinematic, or auto to let the model decide.
enum:
- auto
- '21:9'
- '16:9'
- '4:3'
- '1:1'
- '3:4'
- '9:16'
default: auto
generate_audio:
type: boolean
description: >-
Whether to generate synchronized audio for the video, including
sound effects, ambient sounds, and lip-synced speech. The cost of
video generation is the same regardless of whether audio is
generated or not.
default: true
required:
- prompt
securitySchemes:
bearerAuth:
scheme: bearer
bearerFormat: JWT
type: http
````