neosun100/cosyvoice-docker

🎙️ CosyVoice All-in-One Docker - Production-ready TTS with Web UI, REST API & Voice Cloning

44
/ 100
Emerging

Built on Alibaba's Fun-CosyVoice3-0.5B model with integrated Fun-ASR-Nano for automatic voice transcription, it delivers sub-1.3s time-to-first-byte streaming output via OpenAI-compatible `/v1/audio/speech` endpoints. Features embedding caching (53% latency reduction on repeat voices), custom voice management through reference audio uploads, and multi-language support across Chinese dialects, English, Japanese, Korean, and European languages—all optimized for NVIDIA GPUs with real-time factor performance below 1.0x.

No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 13 / 25
Community 14 / 25

How are scores calculated?

Stars

38

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Jan 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/neosun100/cosyvoice-docker"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.