Download FireRedTTS

Get the latest version of the FireRedTTS open source project

🔥 Recommended Download FireRedTTS-2

Latest version, designed for multi-speaker dialogue generation, providing more natural voice output and reliable speaker switching

FireRedTTS-2 (Recommended)

Latest version, long-form streaming text-to-speech system for multi-speaker dialogue generation

Download FireRedTTS-2

FireRedTTS-1

Basic version, supporting zero-shot voice cloning and emotional voice generation

Download FireRedTTS-1

HuggingFace Demo

Experience FireRedTTS functions online

Visit HuggingFace

FireRedTTS-2 New Features

Long-form Streaming Synthesis

Supports streaming speech synthesis of long-form content to reduce latency and improve user experience

Multi-speaker Dialogue

Optimized for multi-speaker dialogue scenarios to achieve natural speaker switching

Context-aware Prosody

Automatically adjusts voice prosody according to dialogue context to make output more natural

Enhanced Stability

Improved system architecture ensures long-term operational stability and consistency

FireRedTTS-2 Package

Provide multiple different installation packages and instructions for users to download

Complete Installation Package

FireRedTTS complete installation package, including all dependencies and pre-trained models in the complete version

Maintenance Update

FireRedTTS-2 Online Version

FireRedTTS cloud environment, saving computer resources, any computer device can run and experience.

Xiangongyun Online Version

Source Code Package

FireRedTTS-2 project source code, open source community download and use

Download Source Code

System Requirements

  • Python 3.8 or higher
  • PyTorch 1.10 or higher
  • NVIDIA GPU (recommended for acceleration)
  • At least 8GB memory
  • Linux/macOS/Windows (Linux recommended)