> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apistable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice and Persona workflows

> Record, verify, create and reuse a singing voice.

> Operations are enabled individually by server configuration. Disabled operations return 503 without a task. Music credit deduction is currently disabled.

## Recording Voice: four steps

* 1. Submit suno\_voice\_upload with voice\_url and vocal\_start\_s/vocal\_end\_s. Wait for ready:true.
* 2. POST /api/v1/voices/verification\_phrase with voice\_upload\_task\_id and language. This selects the phrase language; voice verification happens in step 3. Call again to regenerate a phrase.
* 3. Record yourself reading phrase\_text, upload the recording and submit suno\_voice\_create with the same upload task ID, phrase\_id and upload\_url. Query the common task endpoint for voice\_id.
* 4. GET /api/v1/voices/\{voice\_id} checks current availability. Provider errors return 503, not a fabricated available:false.

> Languages: en, zh, es, fr, pt, de, ja, ko, hi, ru; default en. The upload session lasts 24 hours after successful preparation; phrase mappings share that deadline. expires\_at:null means the provider phrase TTL is unknown, not unlimited validity. If only the phrase expires, obtain a new phrase; after the upload session expires, upload a new sample and restart.

## Use the verified Voice

Pass the returned voice\_id as persona\_id when generating music, with persona\_model=voice\_persona. Names and descriptions supplied during upload are not automatically inherited: set the final values in suno\_voice\_create.

```json theme={null}
{
  "model": "suno_generate",
  "input": {
    "model": "V6",
    "custom_mode": true,
    "instrumental": false,
    "title": "Paper boats at dawn",
    "style": "Fingerpicked guitar, gentle brushed drums",
    "lyrics": "[Verse]\nWe fold a map into a boat\nAnd let the morning carry it home",
    "persona_id": "YOUR_VOICE_ID",
    "persona_model": "voice_persona"
  }
}
```

## Create from a song

Style Persona: submit suno\_persona\_create with persona\_model=style\_persona and audio\_id. Voice Persona: first suno\_persona\_prepare; then select 10–30 seconds on its prepared vocal timeline and submit suno\_persona\_create with persona\_model=voice\_persona and prepared\_audio\_id. Optional waveform data may be null when the supplier rejects waveform extraction; the prepared vocal audio remains usable. Uploads and their cover/extend derivatives cannot create song Personas.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.