Kyubyong/speaker_adapted_tts

Making a TTS model with 1 minute of speech samples within 10 minutes

32
/ 100
Emerging

This project helps you create a custom text-to-speech (TTS) voice using only a minimal audio sample. You provide just one minute of someone speaking, and it produces a unique voice model that can read any text you give it. This is useful for anyone who needs to generate speech in a specific voice without extensive voice acting or recording sessions, such as content creators or marketing professionals.

184 stars. No commits in the last 6 months.

Use this if you need to quickly generate speech in a custom voice but have very limited audio samples of that speaker.

Not ideal if you need to create a TTS model from scratch without leveraging a pre-existing base model.

voice-over audio-content-creation narration podcast-production virtual-assistants
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

184

Forks

17

Language

License

Last pushed

Mar 20, 2018

Commits (30d)

0

Get this data via API

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

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