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

# Speech synthesis

> Text-to-speech compatible with OpenAI Audio Speech.

**Path:** `POST https://api.omniall.ai/v1/audio/speech`

Response is typically binary audio (`mp3` / `wav` / …) unless upstream returns JSON.

Auth: `Authorization: Bearer sk-...`



## OpenAPI

````yaml openapi/minimax-speech.yaml POST /v1/audio/speech
openapi: 3.1.0
info:
  title: Omniall AI — MiniMax speech
  version: 1.0.0
  description: >-
    OpenAI-compatible text-to-speech (MiniMax TTS via Omniall).


    **Path:** `POST https://api.omniall.ai/v1/audio/speech`


    Extra MiniMax options go in `metadata`. Model examples: `speech-2.8-hd`,
    `speech-2.8-turbo`, `speech-2.6-hd`.


    Auth: `Authorization: Bearer sk-...`
servers:
  - url: https://api.omniall.ai
security: []
paths:
  /v1/audio/speech:
    post:
      tags:
        - MiniMax audio
      summary: Speech synthesis
      description: >-
        Text-to-speech compatible with OpenAI Audio Speech.


        **Path:** `POST https://api.omniall.ai/v1/audio/speech`


        Response is typically binary audio (`mp3` / `wav` / …) unless upstream
        returns JSON.


        Auth: `Authorization: Bearer sk-...`
      operationId: minimaxCreateSpeech
      parameters:
        - name: Authorization
          in: header
          required: true
          schema:
            type: string
            example: Bearer sk-...
          description: Bearer API key.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - input
                - voice
              properties:
                model:
                  type: string
                  description: TTS model id.
                  example: speech-2.8-hd
                input:
                  type: string
                  description: Text to synthesize. May include tone tags like `(laughs)`.
                  example: Hello from Omniall AI
                voice:
                  type: string
                  description: Voice id, e.g. `English_Graceful_Lady`.
                  example: English_Graceful_Lady
                speed:
                  type: number
                  description: Speaking rate.
                response_format:
                  type: string
                  description: Output format, e.g. `mp3`, `wav`, `flac`.
                  example: mp3
                metadata:
                  type: object
                  description: >-
                    MiniMax extensions (`voice_setting`, `audio_setting`,
                    `language_boost`, …).
                  additionalProperties: true
            examples:
              basic:
                summary: Basic TTS
                value:
                  model: speech-2.8-hd
                  input: Hello from Omniall AI
                  voice: English_Graceful_Lady
                  response_format: mp3
              with_metadata:
                summary: With MiniMax metadata
                value:
                  model: speech-2.8-hd
                  input: Welcome to Omniall AI. (laughs) Let's get started.
                  voice: English_Graceful_Lady
                  response_format: mp3
                  metadata:
                    voice_setting:
                      voice_id: English_Graceful_Lady
                      speed: 1
                      vol: 1
                      pitch: 0
                      emotion: happy
                    audio_setting:
                      sample_rate: 32000
                      bitrate: 128000
                      format: mp3
                    language_boost: English
      responses:
        '200':
          description: Audio binary (or provider JSON)
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
            application/json:
              schema:
                type: object

````

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