MiniMax Audio API Documentation

Integrate advanced text-to-speech and voice cloning capabilities into your applications with our powerful API

View Full Documentation

Quick Start

1 Get API Credentials

To access MiniMax APIs, you need to obtain your GroupID and API Key:

  1. Log in to your account at platform.minimax.io
  2. Navigate to Account → Your Profile to find your GroupID
  3. Go to API Keys and click Create New Secret Key
  4. Copy and securely store your API Key (it won't be shown again)

2 Base URL

https://api.minimax.io/

3 Authentication

All API requests require Bearer token authentication:

Authorization: Bearer YOUR_API_KEY

Available Speech Models

speech-2.6-hd

Latest HD Model

Ultimate similarity and ultra-high quality speech synthesis with real-time response and intelligent parsing.

  • 40 languages supported
  • 7 emotions supported
  • Superior prosody and rhythm

speech-2.6-turbo

Latest Turbo Model

Ultimate value with low latency, optimized for cost-effective real-time applications.

  • 40 languages supported
  • 7 emotions supported
  • Fastest processing speed

speech-02-hd

High Quality

Stronger replication similarity with high-quality voice generation and superior rhythm.

  • 24 languages supported
  • 7 emotions supported
  • Excellent cloning similarity

speech-02-turbo

Low Latency

Superior rhythm and stability with enhanced multilingual capabilities and low latency.

  • 24 languages supported
  • 7 emotions supported
  • Fast response time

Text-to-Speech API (T2A)

Endpoint

POST https://api.minimax.io/v1/t2a_v2

Features

  • Up to 10,000 characters per request
  • 300+ system voices available
  • Adjustable volume, pitch, and speed
  • Multiple formats: MP3, PCM, FLAC, WAV
  • Streaming output support
  • Custom cloned voices support

Example Request

curl -X POST https://api.minimax.io/v1/t2a_v2 \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "speech-2.6-hd",
    "text": "Welcome to MiniMax Audio API. Transform your text into natural, expressive speech.",
    "voice_id": "male-qn-qingse",
    "speed": 1.0,
    "vol": 1.0,
    "pitch": 0,
    "audio_sample_rate": 32000,
    "bitrate": 128000,
    "format": "mp3"
  }'

Response

{
  "audio_file": "base64_encoded_audio_data",
  "trace_id": "abc123-def456-ghi789",
  "base_resp": {
    "status_code": 0,
    "status_msg": "success"
  }
}

Voice Cloning API

Endpoint

POST https://api.minimax.io/v1/voice_clone

Features

  • Clone from 10 seconds to 5 minutes audio
  • Formats: MP3, M4A, WAV
  • Custom voice_id definition
  • Voice preview with custom text
  • Noise reduction support
  • Volume normalization option

Example Request

curl -X POST https://api.minimax.io/v1/voice_clone \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "file_id": "YOUR_UPLOADED_FILE_ID",
    "voice_id": "my-custom-voice-01",
    "model": "speech-2.6-hd",
    "text": "This is a test of the cloned voice.",
    "need_noise_reduction": false,
    "need_volumn_normalization": false
  }'

Key Parameters

Parameter Type Description Required
model string Model to use (speech-2.6-hd, speech-2.6-turbo, etc.) Yes
text string Text to synthesize (max 10,000 chars) Yes
voice_id string System voice or custom cloned voice ID Yes
speed float Speech speed (0.5 - 2.0) No
vol float Volume level (0.1 - 10.0) No
pitch int Pitch adjustment (-12 to 12) No
format string Output format (mp3, pcm, flac, wav) No

Additional Resources

Full Documentation

Complete API reference and guides

API Keys

Manage your API credentials

Pricing

View plans and pricing details

Ready to Get Started?

Create your account and get your API key in minutes

Get Your API Key