Skip to main content
POST
/
suno
/
v2
/
voicePersona
/
init
init voice persona
curl --request POST \
  --url https://api.mountsea.ai/suno/v2/voicePersona/init \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "voice_audio_url": "https://example.com/my-voice.wav",
  "language": "zh",
  "vocal_start_s": 0,
  "vocal_end_s": 12.6
}
'
{
  "taskId": "15c257ff-43f7-4678-bd41-202ad6b8488b"
}
This is Phase 1 of the Voice Persona creation workflow. See the full workflow guide for details.
After calling init, poll the returned taskId and wait for status to become awaiting (not success). The data field will contain phrase_text — the text the user must read aloud and record. Once you have the recording, call Complete with the same taskId within 30 seconds.
The language parameter determines the language of the verification phrase. Choose a language that matches the user’s voice audio for best results. Supported: zh, en, ja, ko, es, fr, de, pt, ru, hi.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
voice_audio_url
string<uri>
required

用户原声音频的可下载 URL（WAV/MP3）

Example:

"https://example.com/my-voice.wav"

​
language
string
required

验证短语语言: zh | en | ja | ko | es | fr | de | pt | ru | hi

Example:

"zh"

​
vocal_start_s
number

人声提取起始秒，默认 0

Example:

0

​
vocal_end_s
number

人声提取结束秒，默认由 Suno 自动检测

Example:

12.6

Response

201 - application/json
​
taskId
string
required

task id. Use this id to query task status.

Example:

"15c257ff-43f7-4678-bd41-202ad6b8488b"