
A few days ago, I launched a voice cloning tool at https://voice-clone.org.
The idea is simple: upload a short sample of your voice, and instantly get an AI-generated version that can speak any text you enter.
Typical use cases include:
• Creators who want consistent voiceovers for videos or podcasts without re-recording every time
• Educators who need to generate lecture audio more efficiently
• Builders and demo makers who want to add voice to prototypes and product walkthroughs
• Accessibility projects where someone needs a custom voice for speech
• Personal use like preserving a loved one’s voice or narrating messages
A few details:
• Works entirely in the browser — no training, no config, just record and use
• Free tier available for casual/light use
• MP3 output supported
• Fully open source on GitHub — self-hosting and custom API usage are both possible
⸻
Try it here:
👉 https://voice-clone.org
Code is here:
👉 https://github.com/tanchaowen84/voice-clone
Would love to hear what you might build or experiment with using this. Feedback is welcome.