coqui-ai/TTS-recipes

🐸TTS recipes for different datasets

44
/ 100
Emerging

This helps researchers, linguists, or voice artists quickly train custom text-to-speech models. You provide a dataset of recorded speech and corresponding text transcripts, and it generates a functional text-to-speech voice that can speak new text. It's for anyone needing to create unique synthetic voices from their own audio.

No commits in the last 6 months.

Use this if you have a specific audio dataset and want to build a customized text-to-speech voice from it, without starting from scratch.

Not ideal if you're looking for a ready-to-use text-to-speech voice without training, or if you don't have your own speech datasets.

speech-synthesis voice-cloning audio-research linguistics custom-voice-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

86

Forks

18

Language

Shell

License

MPL-2.0

Last pushed

Jul 26, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/coqui-ai/TTS-recipes"

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