chinokikiss/GSV-TTS-Lite

GSV-TTS-Lite A high-performance inference engine specifically designed for the GPT-SoVITS text-to-speech model.(few shot voice cloning)

59
/ 100
Established

Implements millisecond-level latency through deep optimization techniques including Flash Attention support and decoupled timbre-emotion control, achieving 3-4x speedup on consumer GPUs while halving VRAM requirements. Provides multiple inference modes (streaming token-level output, batch processing, voice conversion) with subtitle timestamp alignment, and ships as a PyPI package supporting CUDA, MPS (Apple Silicon), and CPU backends via Python SDK, REST API, and WebUI interfaces.

57 stars and 1,459 monthly downloads. Available on PyPI.

Maintenance 13 / 25
Adoption 15 / 25
Maturity 20 / 25
Community 11 / 25

How are scores calculated?

Stars

57

Forks

6

Language

Python

License

MIT

Last pushed

Mar 14, 2026

Monthly downloads

1,459

Commits (30d)

0

Dependencies

18

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/chinokikiss/GSV-TTS-Lite"

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