FireRedTeam/FireRedTTS

An Open-Sourced LLM-empowered Foundation TTS System

46
/ 100
Emerging

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.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

905

Forks

83

Language

Python

License

MPL-2.0

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.