neosapience/editts

Official implementation of EdiTTS: Score-based Editing for Controllable Text-to-Speech (INTERSPEECH 2022)

42
/ 100
Emerging

This tool helps you precisely edit generated speech audio without needing to re-create the entire sound from scratch. You provide text with marked segments and specify changes to pitch or content, and it outputs natural-sounding, edited audio files. This is ideal for content creators, voice-over artists, or anyone needing to fine-tune synthetic speech.

121 stars. No commits in the last 6 months.

Use this if you need to make specific, localized adjustments to synthesized speech, such as altering a word or changing the pitch of a sentence, without re-generating the whole audio from scratch.

Not ideal if you need to generate entirely new speech from text without any editing requirements, or if you prefer a graphical user interface for audio manipulation.

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

How are scores calculated?

Stars

121

Forks

17

Language

Python

License

Last pushed

Jan 24, 2023

Commits (30d)

0

Get this data via API

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

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