Before you use it
The app's code is open source (AGPL-3.0), but its default voice model (OmniVoice) is licensed for non-commercial use only, and the maker sells a paid Pro licence for commercial use. Check the licences before using it for anything that earns money.
Why it's useful
Clone a voice or design a new one and narrate as much as you like without paying per character. Also dubs video into other languages. Check each voice model's licence before using it for paid work; the default one is non-commercial.
What it needs
A reasonably powerful computer; a graphics card makes it much faster. Still in beta.
Image: debpalash. VoiceStudio belongs to debpalash; we just think it's worth knowing about.
More tools like this
Open source · MITAudio & Voice
Handy
by CJ Pais
Free, open-source push-to-talk speech-to-text that runs on your own computer.
Open source · Apache-2.0Audio & Voice
OmniVoice
by k2-fsa
Voice cloning and text to speech in over 600 languages, from an open research team.
Open source · MITAudio & Voice
Unmute
by Kyutai
Kyutai's open-source kit that gives any text model ears and a voice, with interruptible back-and-forth talk.