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

# MiniMax Speech (T2A)

> Synthesizes audio from the input text and returns the audio bytes directly. Billing is per input character.



## OpenAPI

````yaml api-reference/model-api/minimax/openapi/speech/openapi.yaml POST /v1/audio/speech
openapi: 3.1.0
info:
  title: MiniMax Speech (T2A)
  description: MiniMax text-to-speech models via the Upmore OpenAI-compatible audio API
  version: 1.0.0
servers:
  - url: https://api.upmore.net
security:
  - bearerAuth: []
paths:
  /v1/audio/speech:
    post:
      summary: Create speech
      description: >-
        Synthesizes audio from the input text and returns the audio bytes
        directly. Billing is per input character.
      operationId: createSpeechMiniMax
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - input
                - voice
              properties:
                model:
                  type: string
                  enum:
                    - speech-2.8-hd
                    - speech-2.8-turbo
                    - speech-2.6-hd
                    - speech-2.6-turbo
                    - speech-02-hd
                    - speech-02-turbo
                    - speech-01-hd
                    - speech-01-turbo
                  example: speech-2.8-hd
                  description: >-
                    The speech model to use. `hd` variants prioritize fidelity,
                    `turbo` variants prioritize latency.
                input:
                  type: string
                  example: 你好，欢迎使用语音合成服务。
                  description: The text to synthesize. Billed per character.
                voice:
                  type: string
                  example: male-qn-qingse
                  description: >-
                    MiniMax voice ID, e.g. `male-qn-qingse`, `female-shaonv`.
                    Passed through to the provider as `voice_id`.
                response_format:
                  type: string
                  enum:
                    - mp3
                    - wav
                    - flac
                    - aac
                    - pcm
                  default: mp3
                  description: Audio container format of the response.
                speed:
                  type: number
                  minimum: 0.5
                  maximum: 2
                  default: 1
                  description: Playback speed multiplier.
                metadata:
                  type: object
                  additionalProperties: true
                  description: >-
                    Provider-specific fields merged into the upstream MiniMax
                    request, e.g. {"voice_setting": {"emotion": "happy"},
                    "audio_setting": {"sample_rate": 32000}, "language_boost":
                    "Chinese"}. Set {"output_format": "url"} to receive a 302
                    redirect to the audio URL instead of raw bytes.
      responses:
        '200':
          description: Audio synthesized successfully; the response body is the audio file.
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
        '400':
          description: Invalid request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            code:
              type: string
            message:
              type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

````