Show HN: Voice Cloning and Multilingual TTS in One Click (Windows) (github.com)

We've created an open-source alternative to Eleven Labs for voice cloning and multilingual TTS. Key features:

- Clone voices from 15-second samples - 50+ pre-trained celebrity voice models - Support for 100+ languages via Google Translator - Speech recognition with Whisper - One-click Windows installation - AI cover generation with pre-trained models

Demo videos showing podcast creation and multilingual dubbing: https://youtu.be/z8g8LMhoh_o (Podcast) https://youtu.be/ZtyhrZHbW0Y (Original) https://youtu.be/CA4WYdkJrkQ (English) https://youtu.be/hSEe0trPtnQ (Spanish) https://youtu.be/qwExW2sReNc (Chinese)

Try it: https://github.com/abus-aikorea/voice-pro

3 comments

[ 3.4 ms ] story [ 12.0 ms ] thread

codetrotter 1y ago ↗

The readme says that it’s a demo. Sounds more like source available than open source in that case. Or has it changed to open source and the readme is out of date?

Also, is the available source complete or does it download any additional components from your company when you run it that are only available in binary form?

gpm 1y ago ↗

There is a MIT license in the repo. In that sense it's open source.

It's using "Edge TTS", which I believe means using API keys [1] stolen from Microsoft Edge and hoping Microsoft doesn't sue you, non jolly-roger flying internet users beware.

Can't speak to other models and their licenses, I stopped looking after I saw edge-tts since I don't feel the need to use this.

[1] https://github.com/rany2/edge-tts/blob/ac41fb85ab2b2b48fef8a...

baystep 1y ago ↗

Bit weirded out by the idea that it installs via a batch file that the Readme dedicates a chapter on how Windows will flag it as a Trojan. As well as the fact that it mentions it is a 30 minute demo, but only does so buried in the Readme. Just feels suspicious to me.