OwenTyme/voice-zero

Collection of samples suitable for use with zero-shot text to speech engines.

39
/ 100
Emerging

Provides curated voice samples from public domain and Creative Commons sources, preprocessed through a multi-stage pipeline combining RNNoise, Kanade Tokenizer for voice resynthesis, and Resemble Enhance to remove noise, reverb, and artifacts for optimal zero-shot TTS compatibility. Samples are normalized to 7-12 seconds and organized by license, with full attribution chains back to original voice actors and sources, plus a companion directory of synthetic emotional variations generated via Chatterbox voice conversion.

No Package No Dependents
Maintenance 13 / 25
Adoption 4 / 25
Maturity 9 / 25
Community 13 / 25

How are scores calculated?

Stars

5

Forks

2

Language

License

Last pushed

Mar 17, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/OwenTyme/voice-zero"

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