Why it's useful
Wrap your own local or hosted chatbot in fast speech-to-text and text-to-speech so you can talk to it like a phone call, with any persona and voice. The site has a free live demo.
What it needs
An NVIDIA graphics card with at least 16GB of memory, on Linux or Windows via WSL (no Mac), plus a text model to plug in
Image: Kyutai. Unmute belongs to Kyutai; we just think it's worth knowing about.
More tools like this
Open source · MIT 33k stars on GitHub
Audio & Voice
Handy
by CJ Pais
Free, open-source push-to-talk speech-to-text that runs on your own computer.
Open source · Apache-2.0 14.2k stars on GitHub
Audio & Voice
OmniVoice
by k2-fsa
Voice cloning and text to speech in over 600 languages, from an open research team.
Open source · AGPL-3.0 53.7k stars on GitHub
Audio & Voice
VoiceStudio
by debpalash
An open-source, fully local alternative to ElevenLabs: voice cloning, voice design, dubbing and text to speech on your own computer.