Overview
MiniMaxHttpTTSService provides high-quality text-to-speech synthesis using MiniMax’s T2A (Text-to-Audio) API with streaming capabilities, emotional voice control, and support for multiple languages. The service offers various models optimized for different use cases, from low-latency to high-definition audio quality.
MiniMax TTS API Reference
Pipecat’s API methods for MiniMax TTS integration
Example Implementation
Complete example using MiniMax TTS
MiniMax Documentation
Official MiniMax T2A API documentation
MiniMax Platform
Access voice models and API credentials
Installation
To use MiniMax services, no additional dependencies are required beyond the base installation:Prerequisites
MiniMax Account Setup
Before using MiniMax TTS services, you need:- MiniMax Account: Sign up at MiniMax Platform
- API Credentials: Get your API key and Group ID from the platform
- Voice Selection: Choose from available voice models and emotional settings
Required Environment Variables
MINIMAX_API_KEY: Your MiniMax API key for authenticationMINIMAX_GROUP_ID: Your MiniMax group ID
Configuration
MiniMaxHttpTTSService
Deprecated since 0.0.105, removed in 2.0.0. Use
settings=MiniMaxHttpTTSService.Settings(...) instead.Deprecated since 0.0.105, removed in 2.0.0. Use
settings=MiniMaxHttpTTSService.Settings(...) instead.API base URL. Use
https://api.minimaxi.chat/v1/t2a_v2 for mainland China or
https://api-uw.minimax.io/v1/t2a_v2 for western United States.Output audio sample rate in Hz. When
None, uses the pipeline’s configured
sample rate.Deprecated since 0.0.105, removed in 2.0.0. Use
settings=MiniMaxHttpTTSService.Settings(...) instead.Runtime-configurable settings. See Settings below.
Settings
Runtime-configurable settings passed via thesettings constructor argument using MiniMaxHttpTTSService.Settings(...). These can be updated mid-conversation with TTSUpdateSettingsFrame. See Service Settings for details.
Usage
Basic Setup
With Voice Customization
Notes
- HTTP-based streaming: MiniMax uses an HTTP streaming API, not WebSocket. Audio data is returned in hex-encoded PCM chunks.
- Emotional voice control: The
emotionparameter lets you adjust the emotional tone of the voice without changing the voice model itself. - Model selection: The
speech-2.6-*models support additional languages (Filipino, Tamil, Persian). Useturbovariants for lower latency orhdvariants for higher quality. - The Python class is named
MiniMaxHttpTTSService, notMiniMaxTTSService.