OmniVoice turns typed text into natural-sounding audio and covers 646 languages with one model, so you do not need to switch settings for each language. It can also clone a voice from a short audio sample, or design a new custom voice from a text description.
The project is open source under the Apache 2.0 licence. It suits content creators, educators and developers who need voiceovers in many languages, and there is a free way to try it.
