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

# eleven_v3

> Create an asynchronous speech generation task for a selected voice.



## OpenAPI

````yaml /openapi/audio/eleven-v3.yaml post /audio-generation
openapi: 3.0.3
info:
  title: eleven_v3
  version: 1.0.0
  description: Create an asynchronous speech generation task for a selected voice.
  x-linkmodel-sort-weight: 90202602029
servers:
  - url: https://api.linkmodel.ai/api/v1
    description: Production
security:
  - bearerAuth: []
tags:
  - name: ElevenLabs
  - name: audio
paths:
  /audio-generation:
    post:
      tags:
        - ElevenLabs
        - audio
      summary: eleven_v3
      description: >
        Generate speech from text using a selected voice.


        |   |   |

        | --- | --- |

        | **Provider** | ElevenLabs |

        | **Tasks** | text-to-audio |


        ## Create and retrieve audio


        Provide a unique `idempotency_key` in the body or an `Idempotency-Key`
        header. Retrying the same request with the same key returns the original
        task; reusing it with different input is rejected.


        Poll `GET /api/v1/query/audio-generation?task_id=...` until the task
        succeeds or fails. On success, `output_url` is a signed download URL
        valid for 30 minutes; query again after it expires.


        Charges use the provider-reported character-cost units, which are not
        necessarily the number of input characters. Failed final delivery is not
        charged.
      operationId: eleven-v3
      parameters:
        - name: Idempotency-Key
          in: header
          required: false
          description: >-
            Unique key for safe retries. Supply this header or idempotency_key
            in the request body.
          schema:
            type: string
            maxLength: 128
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                model:
                  type: string
                  enum:
                    - eleven_v3
                  description: 'Must be one of: eleven_v3.'
                prompt:
                  type: string
                  minLength: 1
                  description: Text to synthesize, up to 5,000 Unicode characters.
                extends:
                  type: object
                  properties:
                    voice_id:
                      type: string
                      maxLength: 256
                      description: Length must be at most 256.
                      pattern: ^[A-Za-z0-9]+$
                    output_format:
                      type: string
                      enum:
                        - alaw_8000
                        - mp3_22050_32
                        - mp3_24000_48
                        - mp3_44100_128
                        - mp3_44100_192
                        - mp3_44100_32
                        - mp3_44100_64
                        - mp3_44100_96
                        - opus_48000_128
                        - opus_48000_192
                        - opus_48000_32
                        - opus_48000_64
                        - opus_48000_96
                        - pcm_16000
                        - pcm_22050
                        - pcm_24000
                        - pcm_32000
                        - pcm_44100
                        - pcm_48000
                        - pcm_8000
                        - ulaw_8000
                        - wav_16000
                        - wav_22050
                        - wav_24000
                        - wav_32000
                        - wav_44100
                        - wav_48000
                        - wav_8000
                      default: mp3_44100_128
                      maxLength: 64
                      description: >-
                        Must be one of: alaw_8000, mp3_22050_32, mp3_24000_48,
                        mp3_44100_128, mp3_44100_192, mp3_44100_32,
                        mp3_44100_64, mp3_44100_96, opus_48000_128,
                        opus_48000_192, opus_48000_32, opus_48000_64,
                        opus_48000_96, pcm_16000, pcm_22050, pcm_24000,
                        pcm_32000, pcm_44100, pcm_48000, pcm_8000, ulaw_8000,
                        wav_16000, wav_22050, wav_24000, wav_32000, wav_44100,
                        wav_48000, wav_8000. Defaults to `mp3_44100_128`.
                    voice_settings:
                      type: object
                      properties:
                        stability:
                          type: number
                          minimum: 0
                          maximum: 1
                        similarity_boost:
                          type: number
                          minimum: 0
                          maximum: 1
                        style:
                          type: number
                          minimum: 0
                          maximum: 1
                        speed:
                          type: number
                          minimum: 0.25
                          maximum: 4
                        use_speaker_boost:
                          type: boolean
                      description: >-
                        Optional voice controls; omitted fields use voice
                        defaults.
                  required:
                    - voice_id
                idempotency_key:
                  type: string
                  maxLength: 128
                  description: >-
                    Unique key for safe retries. Supply this field or the
                    Idempotency-Key header.
              required:
                - model
                - prompt
                - extends
      responses:
        '200':
          description: >-
            Task accepted. A successful response returns code 0 and
            data.task_id; it does not mean generation has completed.
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: integer
                    example: 0
                  msg:
                    type: string
                  request_id:
                    type: string
                  data:
                    type: object
                    properties:
                      task_id:
                        type: string
                      status:
                        type: string
        '401':
          description: Missing or invalid API key.
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT

````

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