CMsmartvoice/One-Shot-Voice-Cloning

:relaxed: One Shot Voice Cloning base on Unet-TTS

38
/ 100
Emerging

This project helps you create new speech in a specific voice, even if you only have a short sample of that voice. You provide a piece of text you want to be spoken and a short audio recording of the target voice, and it generates the audio of the text spoken in that voice. It's useful for anyone who needs to generate natural-sounding speech for various applications, like content creators, educators, or those building custom audio experiences.

245 stars. No commits in the last 6 months.

Use this if you need to generate high-quality, custom audio speech that mimics a specific voice using only a single reference audio clip.

Not ideal if you need to clone voices that express strong, out-of-domain emotions, as the training data focuses on neutral speech.

voice-generation audio-content-creation speech-synthesis narration digital-voice-avatars
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 20 / 25

How are scores calculated?

Stars

245

Forks

43

Language

Jupyter Notebook

License

Last pushed

Mar 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/CMsmartvoice/One-Shot-Voice-Cloning"

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