SandBase is live — $1 in free credits on signupStart free ›
Start building
Use in agentMiniMax models

MiniMax modelsaudio generation api

minimax/speech/2.8/turbo

MiniMax Speech 2.8 Turbo text-to-speech model with fast voice synthesis, enhanced expressiveness, 40+ language support, and voice cloning.

Input
Text to convert to speech. Use <#x#> between words to control pause duration (0.01-99.99s).
Voice ID for speech synthesis. Use a predefined system voice or a custom cloned voice ID.
0.52
Speech speed. Range: 0.5-2.0, where 1.0 is normal speed. Range: 0.5 to 2.
0.110
Speech volume. Range: 0.1-10.0, where 1.0 is normal volume. Range: 0.1 to 10.
-1212
Speech pitch. Range: -12 to 12, where 0 is normal pitch. Range: -12 to 12.
The emotion of the generated speech. Allowed values: happy, sad, angry, fearful, disgusted, surprised, neutral.
Improves performance in number-reading scenarios.
Sample rate of generated sound. Allowed values: 8000, 16000, 22050, 24000, 32000, 44100.
Bitrate of generated sound. Allowed values: 32000, 64000, 128000, 256000.
The number of channels. 1: mono, 2: stereo. Allowed values: 1, 2.
Format of generated sound. Allowed values: mp3, pcm, flac.
Enhance the ability to recognize specified languages and dialects. Allowed values: 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.
Idle

Example output — click Run to generate your own

API README

MiniMax Speech 2.8 Turbo

MiniMax Speech 2.8 Turbo is a text-to-speech model focused on natural, expressive delivery rather than a mechanically perfect read. It synthesizes a chosen voice from text while preserving conversational rhythm, pauses, emotion, and subtle vocal behaviors that make narration feel present and human.

Speech 2.8 supports native sound tags for breaths, laughter, hesitations, and other non-verbal moments, alongside multilingual delivery and detailed audio controls. The Turbo route balances natural flow with faster, cost-efficient synthesis for production workflows.

Highlights

  • Native sound tags. Interprets breaths, laughter, coughs, hesitations, and other vocal gestures inside the script.
  • Natural rhythm and emotion. Models pacing, pauses, pitch variation, and expressive delivery for less robotic speech.
  • Cross-lingual performance. Supports a broad language set with language boosting for multilingual narration and localization.
  • Fast natural synthesis. Optimizes turnaround while retaining the expressive behavior of the Speech 2.8 generation.

Pricing

ConfigurationBilling unitPrice
Text lengthPer 1,000 characters$0.06

When to Use

✅ Good fit❌ Consider alternatives
The project needs expressive narrationThe goal is a different media task or endpoint
The available inputs match the required local schemaRequired source media or permissions are unavailable
The brief can specify subject, composition, style, and deliveryThe result must be deterministic at pixel or sample level
The supported formats and controls match final placementDelivery requires unsupported dimensions, codecs, or duration
An asynchronous generated result fits the workflowA live, frame-synchronous, or real-time response is mandatory

Prompt Guide

Write the request as a production brief: identify the main subject or source material, state the intended transformation, describe composition or timing, and finish with style, atmosphere, and delivery constraints. Keep preservation requirements separate from requested changes, and use only fields exposed by this route.

{
  "text": "Hello, welcome to Sandbase",
  "voice_id": "Wise_Woman",
  "pitch": 0,
  "speed": 1,
  "format": "mp3"
}

Technical Specs

SpecValue
Model IDminimax/speech/2.8/turbo
Input fieldstext (string)<br>pitch (integer; -12–12)<br>speed (number; 0.5–2)<br>format (string; mp3, pcm, flac)<br>volume (number; 0.1–10)<br>bitrate (integer; 32000, 64000, 128000, 256000)<br>channel (integer; 1, 2)<br>emotion (string; happy, sad, angry, fearful, disgusted, surprised, neutral)<br>voice_id (string)<br>sample_rate (integer; 8000, 16000, 22050, 24000, 32000, 44100)<br>language_boost (string; 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)<br>english_normalization (boolean)
Required inputtext, voice_id
Output fieldsurl, duration_ms, content_type
ExecutionAsynchronous job

Related Models

  • minimax/speech/2.8/hd
  • minimax/voice-clone
  • minimax/music/v2

Related Models

minimax/speech/2.8/hdMiniMax Speech 2.8 HD text-to-speech model with high-definition voice synthesis, enhanced expressiveness, 40+ language support, and voice cloning.minimax/speech/02-hdSpeech 02 Hd by MiniMax - convert text to natural-sounding speech with AI. Supports multiple voices, languages, emotions, and speaking styles for content creation and accessibility.minimax/speech/02-turboSpeech 02 Turbo is MiniMax's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.minimax/speech/2.6/hdMiniMax Speech 2.6 HD text-to-speech model with high-definition voice synthesis, 40+ language support, voice cloning, and expressive emotion control.minimax/speech/2.6/turboMiniMax Speech 2.6 Turbo text-to-speech model with fast voice synthesis, 40+ language support, voice cloning, and expressive emotion control.minimax/music/2.6MiniMax Music 2.6 text-to-music model with enhanced quality, lyrics support, instrumental generation, and configurable audio output.minimax/music/v2Music V2 by MiniMax - generate music, sound effects, and audio from text descriptions with AI. Create original compositions, ambient sounds, and audio content for any creative project.minimax/voice-cloneVoice Clone is MiniMax's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.