多角色对话合成
ElevenLabs
Text to Dialogue
Synthesize multi-speaker dialogue audio
POST
多角色对话合成
Synthesize multi-speaker dialogue from an
inputs[] list. Each item has text and voiceId. Maps to ElevenLabs Text to Dialogue:
- Default:
POST /v1/text-to-dialogue/stream withTimestamps=true:POST /v1/text-to-dialogue/stream/with-timestamps
This is an async task. The response contains a
taskId — use Get Task Status to poll. On success, result includes audioUrl. Billing prefers the official characterCost; local textLength is used as a fallback.Constraints
- Up to 100 dialogue lines per request (
inputs) - Up to 10 distinct
voiceIdvalues - Each line: 1–5000 characters; text may include emotion tags such as
[giggling]or[curious]
Recommended Flow
1
List voices
Call List Voices to obtain
voiceId values (and optional previewUrl).2
Create dialogue task
Call
POST /eleven/dialogue with inputs (and optional model, outputFormat, withTimestamps, etc.).3
Poll for audio
Poll
GET /eleven/tasks?taskId=xxx until status is completed, then read result.audioUrl.Models
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
对话台词列表,每项含 text + voiceId
Required array length:
1 - 100 elementsExample:
模型(Dialogue 官方默认 eleven_v3)
Available options:
eleven_v3, eleven_multilingual_v2, eleven_turbo_v2_5, eleven_flash_v2_5 Example:
"eleven_v3"
音频输出格式
Available options:
mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192 Example:
"mp3_44100_128"
是否返回字符级时间戳。true 时走官方 stream/with-timestamps
Example:
false
语言代码 ISO-639-1(部分模型支持)
Example:
"en"
对话生成设置
随机种子
Example:
12345
文本归一化
Available options:
auto, on, off Example:
"auto"
Response
200 - application/json
任务创建成功
任务 ID,用于后续查询结果