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

# Voice Persona 初始化

> 上传语音音频并获取验证短语

<Info>
  这是 Voice Persona 创建工作流程的**第一阶段**。详情请参阅[完整工作流程指南](/zh/api-reference/suno/voicePersona)。
</Info>

调用 init 后，轮询返回的 `taskId`，等待状态变为 **`awaiting`**（不是 `success`）。`data` 字段将包含 `phrase_text` — 用户需要朗读并录制的文本。

获得录音后，在 30 秒内使用**相同的 `taskId`** 调用 [Complete](/zh/api-reference/suno/voicePersonaComplete)。

<Tip>
  `language` 参数决定验证短语的语言。请选择与用户语音音频匹配的语言以获得最佳效果。支持的语言：`zh`、`en`、`ja`、`ko`、`es`、`fr`、`de`、`pt`、`ru`、`hi`。
</Tip>


## OpenAPI

````yaml POST /suno/v2/voicePersona/init
openapi: 3.0.0
info:
  title: Suno AI
  description: API documentation for Suno AI
  version: 1.0.0
  contact: {}
servers:
  - url: https://api.mountsea.ai
    description: API Gateway
security: []
tags:
  - name: suno
    description: ''
paths:
  /suno/v2/voicePersona/init:
    post:
      tags:
        - suno
      summary: init voice persona
      description: >-
        Upload voice audio, extract vox-stem, and get verification phrase. User
        must read the phrase_text aloud and record it for the next step.
      operationId: ApiPublicController_voicePersonaInit
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VoicePersonaInitDto'
      responses:
        '201':
          description: ''
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskIdDto'
      security:
        - bearerAuth: []
components:
  schemas:
    VoicePersonaInitDto:
      type: object
      properties:
        voice_audio_url:
          type: string
          format: uri
          description: 用户原声音频的可下载 URL（WAV/MP3）
          example: https://example.com/my-voice.wav
        language:
          type: string
          description: '验证短语语言: zh | en | ja | ko | es | fr | de | pt | ru | hi'
          example: zh
        vocal_start_s:
          type: number
          description: 人声提取起始秒，默认 0
          example: 0
        vocal_end_s:
          type: number
          description: 人声提取结束秒，默认由 Suno 自动检测
          example: 12.6
      required:
        - voice_audio_url
        - language
    TaskIdDto:
      type: object
      properties:
        taskId:
          type: string
          description: task id. Use this id to query task status.
          example: 15c257ff-43f7-4678-bd41-202ad6b8488b
      required:
        - taskId
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT

````