zaigie/FunSpeech
开箱即用的本地私有化部署语音服务，快速搭建FunASR与CosyVoice2/3后端
Provides alicloud-compatible ASR and TTS APIs built on FunASR and CosyVoice models with WebSocket streaming support. Features multi-model support (including zero-shot voice cloning), intelligent far-field audio filtering for ASR, dynamic model caching, and flexible GPU distribution across multiple worker processes. Integrates with ModelScope for automatic model downloads and supports both synchronous and asynchronous TTS workflows via REST and WebSocket endpoints.
111 stars.
Stars
111
Forks
21
Language
Python
License
MIT
Category
Last pushed
Mar 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/zaigie/FunSpeech"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
PaddlePaddle/PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with...
k2-fsa/sherpa
Speech-to-text server framework with next-gen Kaldi
Picovoice/cheetah
On-device streaming speech-to-text engine powered by deep learning
Picovoice/leopard
On-device speech-to-text engine powered by deep learning
manyeyes/ManySpeech
AI Speech Solutions for Tasks such as ASR, Vocal Extraction, Accompaniment Extraction, Audio...