FireRedTeam/FireRedTTS
An Open-Sourced LLM-empowered Foundation TTS System
Supports streamable inference with both acoustic LLM and flow-matching decoders, enabling real-time speech synthesis from text and reference audio. The system combines autoregressive token generation with neural codec decoding, leveraging HuBERT embeddings for speaker encoding and supporting zero-shot voice cloning across Chinese and multilingual contexts. Built on PyTorch with modular architecture compatible with standard audio processing pipelines.
905 stars. No commits in the last 6 months.
Stars
905
Forks
83
Language
Python
License
MPL-2.0
Category
Last pushed
Sep 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/FireRedTeam/FireRedTTS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
index-tts/index-tts
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
lucasnewman/f5-tts-mlx
Implementation of F5-TTS in MLX
stepfun-ai/Step-Audio-EditX
A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing...
unilight/seq2seq-vc
A sequence-to-sequence voice conversion toolkit.
Edresson/YourTTS
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone