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

# MiniMax Speech 2.8 Turbo Text to Speech

> Create a text-to-speech generation task using the speech-2.8-turbo model.

## Overview

Generate speech from text using the MiniMax Speech 2.8 Turbo model. Speech 2.8 Turbo delivers fast, high-quality synthesis:

* **Fast generation** — optimized for speed with Turbo-tier performance
* **Pause tags** — insert precise pauses with `<#x#>` syntax (x = 0.01-99.99 seconds)
* **Interjection tags** — add natural expressions like `(laughs)`, `(sighs)`, `(coughs)`, `(clears throat)`, `(gasps)`, `(sniffs)`, `(groans)`, `(yawns)`
* **Voice settings** — control speed, volume, pitch, and emotion
* **40+ languages** — extensive language support with language boost
* **Audio customization** — configurable format (MP3/PCM/FLAC), sample rate, channel, and bitrate
* **Voice modification** — fine-tune pitch, intensity, and timbre
* **Pronunciation dictionary** — custom pronunciation replacements
* **Loudness normalization** — professional audio level control

## Supported Voice IDs

Speech 2.8 Turbo supports the same 223+ system voice IDs as Speech 2.8 HD, covering 20+ languages including Chinese (Mandarin), Chinese (Cantonese), English, Japanese, Korean, Spanish, Portuguese, French, Indonesian, German, Russian, Italian, Arabic, Turkish, Ukrainian, Dutch, Vietnamese, Thai, Polish, Romanian, Greek, Czech, Finnish, and Hindi.

See the [Speech 2.8 HD documentation](/docs/docs/api-reference/endpoint/minimax/speech-2.8-hd/text-to-speech) for the complete voice ID list.


## OpenAPI

````yaml api-reference/endpoint/minimax/speech-2.8-turbo/speech-2.8-turbo.yaml POST /vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation
openapi: 3.1.0
info:
  title: MiniMax Speech 2.8 Turbo API
  description: MiniMax Speech 2.8 Turbo - Text-to-Speech Generation
  version: 2.0.0
servers:
  - url: https://api.mulerouter.ai/
security:
  - bearerAuth: []
paths:
  /vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation:
    post:
      summary: Create Speech Generation Task
      description: >-
        Create a text-to-speech generation task using the speech-2.8-turbo
        model.
      operationId: speech_2_8_turbo_create
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SpeechGenerationRequest'
            example:
              prompt: Hello, this is a test of speech synthesis.
              voice_setting:
                voice_id: Wise_Woman
                speed: 1
                vol: 1
                pitch: 0
              output_format: url
      responses:
        '202':
          description: Accepted - Task created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
              example:
                task_info:
                  id: 8e1e315e-b50d-4334-a231-be7d19a372f4
                  status: pending
                  created_at: '2026-03-03T00:00:00Z'
                  updated_at: '2026-03-03T00:00:00Z'
components:
  schemas:
    SpeechGenerationRequest:
      type: object
      required:
        - prompt
      properties:
        prompt:
          type: string
          minLength: 1
          maxLength: 10000
          description: >
            Text to convert to speech. Use `<#x#>` for pauses (x = 0.01-99.99
            seconds). Supports interjection tags: `(laughs)`, `(sighs)`,
            `(coughs)`, `(clears throat)`, `(gasps)`, `(sniffs)`, `(groans)`,
            `(yawns)`.
        voice_setting:
          $ref: '#/components/schemas/VoiceSetting'
          description: Voice configuration settings (optional, defaults to Wise_Woman).
        audio_setting:
          anyOf:
            - $ref: '#/components/schemas/AudioSetting'
            - type: 'null'
          description: Audio configuration settings.
        language_boost:
          anyOf:
            - type: string
              enum:
                - Chinese
                - Chinese,Yue
                - English
                - Arabic
                - Russian
                - Spanish
                - French
                - Portuguese
                - German
                - Turkish
                - Dutch
                - Ukrainian
                - Vietnamese
                - Indonesian
                - Japanese
                - Italian
                - Korean
                - Thai
                - Polish
                - Romanian
                - Greek
                - Czech
                - Finnish
                - Hindi
                - Bulgarian
                - Danish
                - Hebrew
                - Malay
                - Slovak
                - Swedish
                - Croatian
                - Hungarian
                - Norwegian
                - Slovenian
                - Catalan
                - Nynorsk
                - Afrikaans
                - auto
            - type: 'null'
          description: Enhance recognition of specified languages and dialects.
        output_format:
          type: string
          enum:
            - url
            - hex
          default: hex
          description: 'Format of the output content (non-streaming only). Default: hex.'
        pronunciation_dict:
          anyOf:
            - $ref: '#/components/schemas/PronunciationDict'
            - type: 'null'
          description: Custom pronunciation dictionary for text replacement.
        normalization_setting:
          anyOf:
            - $ref: '#/components/schemas/LoudnessNormalizationSetting'
            - type: 'null'
          description: Loudness normalization settings for the audio.
        voice_modify:
          anyOf:
            - $ref: '#/components/schemas/VoiceModify'
            - type: 'null'
          description: Voice modification settings to adjust pitch, intensity, and timbre.
    TaskCreatedResponse:
      type: object
      properties:
        task_info:
          $ref: '#/components/schemas/TaskInfoCreated'
    VoiceSetting:
      type: object
      properties:
        voice_id:
          type: string
          description: >-
            Voice ID for synthesis. Examples - Chinese: male-qn-qingse,
            female-shaonv, female-yujie; English: Charming_Lady,
            English_Trustworthy_Man, English_Graceful_Lady. See the Supported
            Voice IDs section in the overview for the full list.
        speed:
          type: number
          minimum: 0.5
          maximum: 2
          default: 1
          description: Speech speed, range [0.5, 2.0].
        vol:
          type: number
          minimum: 0.01
          maximum: 10
          default: 1
          description: Volume, range [0, 10].
        pitch:
          type: integer
          minimum: -12
          maximum: 12
          default: 0
          description: Voice pitch, range [-12, 12].
        emotion:
          anyOf:
            - type: string
              enum:
                - happy
                - sad
                - angry
                - fearful
                - disgusted
                - surprised
                - neutral
            - type: 'null'
          description: Emotion of the generated speech.
        english_normalization:
          type: boolean
          default: false
          description: >-
            Enables English text normalization to improve number reading
            performance.
    AudioSetting:
      type: object
      properties:
        format:
          type: string
          enum:
            - mp3
            - pcm
            - flac
          default: mp3
          description: Audio format.
        sample_rate:
          type: integer
          enum:
            - 8000
            - 16000
            - 22050
            - 24000
            - 32000
            - 44100
          default: 32000
          description: Sample rate of generated audio (Hz).
        channel:
          type: integer
          enum:
            - 1
            - 2
          default: 1
          description: Number of audio channels (1=mono, 2=stereo).
        bitrate:
          type: integer
          enum:
            - 32000
            - 64000
            - 128000
            - 256000
          default: 128000
          description: Bitrate of generated audio (bps).
    PronunciationDict:
      type: object
      properties:
        tone_list:
          type: array
          items:
            type: string
          description: >-
            List of pronunciation replacements in format
            ['text/(pronunciation)', ...].
    LoudnessNormalizationSetting:
      type: object
      properties:
        enabled:
          type: boolean
          default: true
          description: Enable loudness normalization for the audio.
        target_loudness:
          type: number
          minimum: -70
          maximum: -10
          default: -18
          description: Target loudness in LUFS.
        target_range:
          type: number
          minimum: 0
          maximum: 20
          default: 8
          description: Target loudness range in LU.
        target_peak:
          type: number
          minimum: -3
          maximum: 0
          default: -0.5
          description: Target peak level in dBTP.
    VoiceModify:
      type: object
      properties:
        pitch:
          type: integer
          minimum: -100
          maximum: 100
          default: 0
          description: 'Pitch adjustment. Range: -100 to 100.'
        intensity:
          type: integer
          minimum: -100
          maximum: 100
          default: 0
          description: 'Intensity/energy of the voice. Range: -100 to 100.'
        timbre:
          type: integer
          minimum: -100
          maximum: 100
          default: 0
          description: 'Timbre adjustment. Range: -100 to 100.'
    TaskInfoCreated:
      type: object
      required:
        - id
        - status
        - created_at
        - updated_at
      properties:
        id:
          type: string
          format: uuid
        status:
          type: string
          enum:
            - pending
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

````