OmniVoice is an open-source speech synthesis model that generates audio from text and supports voice cloning. It is distributed through Hugging Face for developers and researchers to run locally or integrate into applications.
OmniVoice is a Voice, TTS & speech project. It focuses on generating natural-sounding speech and cloned voices without relying on a hosted proprietary API. OmniVoice is an open-source project aimed at AI developers and speech researchers. OmniVoice is open source under the Apache-2.0 license. It runs on the command line, and it can be self-hosted.
k2-fsa builds and maintains OmniVoice, and it first shipped in 2026. The project is developed in the open on GitHub with 8.8k stars and 21 commits in the last 90 days. Among its 5 catalogued features are text-to-speech, voice cloning, and speech synthesis.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do