---
title: "Create voice persona"
method: POST
path: "/suno/persona/voice/create"
---

# Create voice persona

`POST /suno/persona/voice/create`

## Request body

- object
  - `name` string, required — Persona name
  - `description` string — Persona description
  - `image_s3_id` string — Image in Base64 format (data:image/jpeg;base64,...)
  - `is_public` boolean — Whether the persona is public (note: always reset to false regardless of input)
  - `persona_type` 'vox', required — Must be vox
  - `vocal_start_s` number — Vocal start time (seconds)
  - `vocal_end_s` number — Vocal end time (seconds)
  - `user_input_styles` string — Style description
  - `source` string — Source type
  - `singer_skill_level` 'Advanced' | 'Intermediate' | 'Beginner' | 'Professional' — Singer skill level
  - `is_voice_recording` boolean — Whether this is a voice recording
  - `vox_audio_id` string, required — vox_audio_id from the upload voice step
  - `voice_recording_id` string, required — voice_recording_id from the upload voice step
  - `verification_id` string, required — verification_id from the voice verification step

## Response `200`

Success

- object
  - `id` string — Successfully created persona_id

---

[API](https://skmtc.net/deerapi/apis/text-to-audio-api.md) · [All operations](https://skmtc.net/deerapi/apis/text-to-audio-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/deerapi/text-to-audio-api/versions/b6265ced74a1/schema)