WangHelin1997/SSR-Speech

SSR-Speech: Towards Stable, Safe and Robust Zero-shot Speech Editing and Synthesis

41
/ 100
Emerging

This project helps content creators, voice artists, and marketing professionals quickly edit existing speech or generate new speech from text. You input an audio clip and a desired transcript, and it outputs a new audio clip with the speech edited or entirely synthesized. It's designed for anyone needing to modify spoken content or create natural-sounding voiceovers without professional studio equipment.

147 stars. No commits in the last 6 months.

Use this if you need to seamlessly change words in an existing audio recording or create new spoken content from a script, ensuring the output sounds natural and stable, even for challenging edits.

Not ideal if you need fine-grained control over individual phonemes or highly nuanced emotional expression, as its focus is on zero-shot generation and editing rather than detailed linguistic manipulation.

audio-editing voice-synthesis content-creation podcasting media-production
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

147

Forks

17

Language

Python

License

MIT

Last pushed

Jan 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/WangHelin1997/SSR-Speech"

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