voice-cloning-app/Voice-Cloning-App

A Python/Pytorch app for easily synthesising human voices

49
/ 100
Emerging

This app helps content creators, podcasters, or voice actors generate new speech in a custom voice from text. You provide existing audio recordings of a voice, and it learns to mimic it. The output is synthesized audio that sounds like the original speaker, saying whatever new text you've provided.

1,443 stars. No commits in the last 6 months.

Use this if you need to create custom voiceovers, narrations, or dialogue in a specific voice without re-recording a human speaker.

Not ideal if you don't have existing audio recordings of the voice you want to clone or if you need real-time voice modification rather than text-to-speech.

voice-generation audio-content-creation text-to-speech podcast-production narration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

1,443

Forks

238

Language

Python

License

BSD-3-Clause

Last pushed

Dec 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/voice-cloning-app/Voice-Cloning-App"

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