OpenVox is a Python package for running an offline voice engine with streaming speech-to-text, text-to-speech, voice cloning, enrollment, and audio enhancement. It also supports an LLM voice-agent loop for developers building on-device, privacy-focused voice applications and robotics systems.
In the Other voice & speech space, OpenVox takes a focused approach. It focuses on running speech recognition, speech synthesis, voice cloning, and voice agents without sending audio to cloud services. OpenVox is a B2B product aimed at developers building privacy-focused voice applications and robotics systems. It ships for the command line, and it can be self-hosted.
It is developed by headlessripper, and it first shipped in 2025. Development happens publicly on GitHub with 117 commits in the last 90 days. Among its 8 catalogued features are streaming speech recognition, text to speech, and voice cloning.
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