create voice persona from audio (instant clone)
curl --request POST \
--url https://api.mountsea.ai/suno/v2/voices \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"audio_url": "https://example.com/voice.mp3",
"name": "My Voice",
"description": "<string>",
"is_public": false,
"vocal_start_s": 0,
"vocal_end_s": 30
}
'import requests
url = "https://api.mountsea.ai/suno/v2/voices"
payload = {
"audio_url": "https://example.com/voice.mp3",
"name": "My Voice",
"description": "<string>",
"is_public": False,
"vocal_start_s": 0,
"vocal_end_s": 30
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
audio_url: 'https://example.com/voice.mp3',
name: 'My Voice',
description: '<string>',
is_public: false,
vocal_start_s: 0,
vocal_end_s: 30
})
};
fetch('https://api.mountsea.ai/suno/v2/voices', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.mountsea.ai/suno/v2/voices",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'audio_url' => 'https://example.com/voice.mp3',
'name' => 'My Voice',
'description' => '<string>',
'is_public' => false,
'vocal_start_s' => 0,
'vocal_end_s' => 30
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.mountsea.ai/suno/v2/voices"
payload := strings.NewReader("{\n \"audio_url\": \"https://example.com/voice.mp3\",\n \"name\": \"My Voice\",\n \"description\": \"<string>\",\n \"is_public\": false,\n \"vocal_start_s\": 0,\n \"vocal_end_s\": 30\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.mountsea.ai/suno/v2/voices")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"audio_url\": \"https://example.com/voice.mp3\",\n \"name\": \"My Voice\",\n \"description\": \"<string>\",\n \"is_public\": false,\n \"vocal_start_s\": 0,\n \"vocal_end_s\": 30\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.mountsea.ai/suno/v2/voices")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"audio_url\": \"https://example.com/voice.mp3\",\n \"name\": \"My Voice\",\n \"description\": \"<string>\",\n \"is_public\": false,\n \"vocal_start_s\": 0,\n \"vocal_end_s\": 30\n}"
response = http.request(request)
puts response.read_body{
"taskId": "15c257ff-43f7-4678-bd41-202ad6b8488b"
}Voice Persona
Clone Voice
Paid one-step Voice Persona — same official flow as Init + Complete
POST
/
suno
/
v2
/
voices
create voice persona from audio (instant clone)
curl --request POST \
--url https://api.mountsea.ai/suno/v2/voices \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"audio_url": "https://example.com/voice.mp3",
"name": "My Voice",
"description": "<string>",
"is_public": false,
"vocal_start_s": 0,
"vocal_end_s": 30
}
'import requests
url = "https://api.mountsea.ai/suno/v2/voices"
payload = {
"audio_url": "https://example.com/voice.mp3",
"name": "My Voice",
"description": "<string>",
"is_public": False,
"vocal_start_s": 0,
"vocal_end_s": 30
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
audio_url: 'https://example.com/voice.mp3',
name: 'My Voice',
description: '<string>',
is_public: false,
vocal_start_s: 0,
vocal_end_s: 30
})
};
fetch('https://api.mountsea.ai/suno/v2/voices', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.mountsea.ai/suno/v2/voices",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'audio_url' => 'https://example.com/voice.mp3',
'name' => 'My Voice',
'description' => '<string>',
'is_public' => false,
'vocal_start_s' => 0,
'vocal_end_s' => 30
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.mountsea.ai/suno/v2/voices"
payload := strings.NewReader("{\n \"audio_url\": \"https://example.com/voice.mp3\",\n \"name\": \"My Voice\",\n \"description\": \"<string>\",\n \"is_public\": false,\n \"vocal_start_s\": 0,\n \"vocal_end_s\": 30\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.mountsea.ai/suno/v2/voices")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"audio_url\": \"https://example.com/voice.mp3\",\n \"name\": \"My Voice\",\n \"description\": \"<string>\",\n \"is_public\": false,\n \"vocal_start_s\": 0,\n \"vocal_end_s\": 30\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.mountsea.ai/suno/v2/voices")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"audio_url\": \"https://example.com/voice.mp3\",\n \"name\": \"My Voice\",\n \"description\": \"<string>\",\n \"is_public\": false,\n \"vocal_start_s\": 0,\n \"vocal_end_s\": 30\n}"
response = http.request(request)
puts response.read_body{
"taskId": "15c257ff-43f7-4678-bd41-202ad6b8488b"
}Clone Voice (
Returns Task result (
Copy
Use on
POST /suno/v2/voices) is a Voice Persona API. It runs the same official flow as Init + Complete in one async task: upload → vox stem → phrase → TTS verify → create.
You only send a public audio_url. The phrase / TTS step is internal — no second recording UI. Init + Complete is unchanged and still free.
Billed. Failed Clone Voice tasks should not be billed. See Persona overview.
On
/generate send persona.persona_id + persona.is_voice: true. artist_clip_id is optional for Voice Persona (persona_id alone selects task vox). Same-account ById — stay on the creating account.Request
| Field | Type | Required | Description |
|---|---|---|---|
audio_url | string (URL) | Yes | Publicly downloadable reference audio (MP3/WAV). Duration 10–240s; 30–60s dry solo vocal recommended |
name | string | No | Voice name; generated if omitted |
description | string | No | Voice description |
is_public | boolean | No | Publish to official Suno. Default false. true lists the voice on the official plaza |
vocal_start_s | number | No | Vocal range start (seconds). Omit and Suno detects the range |
vocal_end_s | number | No | Vocal range end (seconds). Omit and Suno detects the range |
Create task
curl -X POST "https://api.mountsea.ai/suno/v2/voices" \
-H "Authorization: Bearer your-api-key" \
-H "Content-Type: application/json" \
-d '{
"audio_url": "https://example.com/voice.mp3",
"name": "My Voice",
"is_public": false
}'
{ "taskId": "..." }. Poll Get Task Status until status is success.
Task result (data when success)
Copy persona_id. artist_clip_id may also be present — optional on later /generate:
{
"name": "voices-ext-fix-verify",
"is_public": false,
"persona_id": "af88153e-a513-432a-a9b5-3948fb562d4b",
"artist_clip_id": "clip_abc123"
}
| Field | Type | Description |
|---|---|---|
persona_id | string | Voice Persona ID for /generate (is_voice: true) |
artist_clip_id | string | Root / style clip from this create, when present. Optional on /generate for Voice Persona |
name | string | Display name |
is_public | boolean | Whether it was published to official Suno |
Use on /generate
{
"task": "create",
"model": "chirp-v6",
"prompt": "[Verse]\n...",
"persona": {
"persona_id": "af88153e-a513-432a-a9b5-3948fb562d4b",
"is_voice": true
}
}
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
公网可下载的参考音频 URL,MP3/WAV,时长 10240 秒,建议 3060 秒单人干声
Example:
"https://example.com/voice.mp3"
音色名称;不传则由系统生成
Example:
"My Voice"
音色描述
是否公开到官方 Suno。默认 false。true 时该声线会出现在官方广场。
Example:
false
人声区间起点(秒)。不传则官方自动检测,与旧平台 voices 一致。
Example:
0
人声区间终点(秒)。不传则官方自动检测,与旧平台 voices 一致。
Example:
30
Response
201 - application/json
task id. Use this id to query task status.
Example:
"15c257ff-43f7-4678-bd41-202ad6b8488b"