adasegroup/OSM-one-shot-multispeaker

Framework for one-shot multispeaker system based on Deep Learning

34
/ 100
Emerging

This project helps create speech that sounds like a specific person, even if you only have a short audio sample of their voice. You provide an audio recording of the desired voice and the text you want spoken, and it generates audio where that text is read in the cloned voice. This is useful for anyone who needs to generate natural-sounding speech in various voices, like content creators, voiceover artists, or developers building custom voice assistants.

No commits in the last 6 months.

Use this if you need a flexible way to integrate text-to-speech with custom voice cloning into your applications or workflows, allowing you to swap different voice processing components.

Not ideal if you're looking for a simple, out-of-the-box solution for basic text-to-speech without the need for advanced voice cloning customization or modularity.

voice-cloning text-to-speech audio-content-creation synthetic-media voice-assistant-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

19

Forks

3

Language

Python

License

MIT

Last pushed

May 30, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/adasegroup/OSM-one-shot-multispeaker"

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