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)

54
/ 100
Established

This project helps content creators, educators, or anyone needing custom voices quickly generate speech from text. You provide a short audio sample of a voice, some text describing its style, and the text you want to convert. The output is a high-quality audio file that sounds like the voice you provided, speaking your new text. This is ideal for those who need personalized narration or character voices for their projects.

Available on PyPI.

Use this if you need to rapidly create custom voiceovers or dialogue in Chinese, Japanese, or English, with specific vocal styles and low computational resources.

Not ideal if you need extreme voice conversion quality comparable to dedicated voice-changing models or if your primary need is not text-to-speech.

content-creation voiceover e-learning audiobook-production virtual-assistants
Maintenance 13 / 25
Adoption 8 / 25
Maturity 22 / 25
Community 11 / 25

How are scores calculated?

Stars

57

Forks

6

Language

Python

License

MIT

Last pushed

Mar 14, 2026

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.