Building an open-source ElevenLabs-like AI voice platform called OmniVoice Studio.

It supports voice cloning, dubbing, transcription, and local/self-hosted workflows with Docker + desktop UI support.

Using open-source models like Whisper, Qwen, OmniVoice and more.

https://github.com/debpalash/OmniVoice-Studio

Thanks for checking it out

almost got fooled by blue being green or vice versa. nice experiment!

Few things actually

Yupcha AI Interviewer, handles the screening, video interviewing with conversational agents.

Check it out https://yupcha.com

Working on a oss video dubbing, cloning and design studio

Check out https://github.com/debpalash/OmniVoice-Studio

Suggestions are welcome.