Crie uma voz projetada

OpenAPI

openapi: 3.1.0
info:
  title: CosyVoice Voice Design API — Create voice
  version: 1.0.0
servers:
  - url: https://maas.qwencloudapi.com/api/v1
    description: Singapore
security:
  - BearerAuth: []
paths:
  /services/audio/tts/customization:
    post:
      operationId: createVoiceDesignCosyVoice
      summary: Create a designed voice
      description: Design a voice from a text description for CosyVoice TTS models. Returns a `voice_id` and Base64-encoded preview audio.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/CreateRequest"
      responses:
        "200":
          description: Voice created successfully
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/CreateResponse"
      x-codeSamples:
        - lang: bash
          label: cURL
          source: |-
            curl -X POST https://maas.qwencloudapi.com/api/v1/services/audio/tts/customization \
            -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
            -H "Content-Type: application/json" \
            -d '{
              "model": "voice-enrollment",
              "input": {
                "action": "create_voice",
                "target_model": "cosyvoice-v3.5-plus",
                "voice_prompt": "A composed middle-aged male announcer with a deep, rich voice",
                "preview_text": "Dear listeners, hello everyone",
                "prefix": "announcer",
                "language_hints": ["en"]
              },
              "parameters": {
                "sample_rate": 24000,
                "response_format": "wav"
              }
            }'
components:
  schemas:
    CreateRequest:
      type: object
      required:
        - model
        - input
      properties:
        model:
          type: string
          description: Fixed to `voice-enrollment` (shared with voice cloning).
          enum:
            - voice-enrollment
          example: voice-enrollment
        input:
          type: object
          required:
            - action
            - target_model
            - voice_prompt
            - preview_text
            - prefix
          properties:
            action:
              type: string
              description: Fixed to `create_voice` (same as voice cloning).
              enum:
                - create_voice
              example: create_voice
            target_model:
              type: string
              description: Speech synthesis model for the designed voice. Must match the model in subsequent synthesis calls.
              enum:
                - cosyvoice-v3.5-plus
                - cosyvoice-v3.5-flash
                - cosyvoice-v3-plus
                - cosyvoice-v3-flash
              example: cosyvoice-v3.5-plus
            voice_prompt:
              type: string
              description: Voice description. Chinese and English only. Max 500 characters.
              maxLength: 500
              example: A composed middle-aged male announcer with a deep, rich voice
            preview_text:
              type: string
              description: Text for the preview audio. Chinese and English only. Min 15 characters, max 200 characters.
              minLength: 15
              maxLength: 200
              example: Dear listeners, hello everyone
            prefix:
              type: string
              description: "Voice name prefix. Alphanumeric only, max 10 characters. Generated voice name format: `{target_model}-vd-{prefix}-{unique_id}`."
              maxLength: 10
              pattern: ^[a-zA-Z0-9]+$
              example: announcer
            language_hints:
              type: array
              items:
                type: string
              description: "Specifies the language tendency of the generated voice. Must match the `preview_text` language. Only the first element is used. Supported: `zh`, `en`."
              default:
                - zh
              example:
                - en
        parameters:
          type: object
          description: Preview audio settings.
          properties:
            sample_rate:
              type: integer
              description: Sample rate in Hz for the preview audio.
              enum:
                - 16000
                - 24000
                - 48000
              default: 24000
              example: 24000
            response_format:
              type: string
              description: Audio format for the preview.
              enum:
                - pcm
                - wav
                - mp3
              default: wav
              example: wav
    CreateResponse:
      type: object
      properties:
        output:
          type: object
          properties:
            voice_id:
              type: string
              description: Generated voice ID. Pass as the `voice` parameter in CosyVoice synthesis calls.
              example: cosyvoice-v3.5-plus-vd-announcer-xxxxxx
            preview_audio:
              type: object
              description: Preview audio data.
              properties:
                data:
                  type: string
                  description: Base64-encoded preview audio.
                  example: "{base64_encoded_audio}"
                sample_rate:
                  type: integer
                  description: Sample rate of the preview audio in Hz.
                  example: 24000
                response_format:
                  type: string
                  description: Format of the preview audio.
                  example: wav
            target_model:
              type: string
              description: Speech synthesis model bound to this voice.
              example: cosyvoice-v3.5-plus
        usage:
          type: object
          properties:
            count:
              type: integer
              description: Billed voice creation operations. Always `1`.
              example: 1
        request_id:
          type: string
          description: Request ID for troubleshooting.
          example: xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: DashScope API key. Get one at [API key](/api-reference/preparation/api-key).