
Just found this and it’s actually solid.
An open-source voice synthesis tool that lets you clone voices and generate speech locally. No subscriptions, no cloud needed.
What’s interesting is everything runs on your own machine, so your data stays private.
You can:
• Clone a voice from just a short audio sample
• Generate speech in multiple languages
• Apply effects like pitch, reverb, and filters
• Create multi-speaker conversations with a timeline editor
• Use it as an API for your own projects
It’s basically a free alternative to tools like ElevenLabs, but without the limits.
Good for:
• Content creators doing voiceovers
• Devs building voice apps
• Anyone experimenting with AI audio
Setup might take a bit depending on your system, but once it’s running, it’s pretty powerful.