audio.cpp-gguf hosts GGUF quantized versions of multiple speech models for text-to-speech, voice conversion, source separation, and speaker diarization. These files are built for direct use with the audio.cpp library and include detailed compatibility notes and validation guidance for developers building local audio applications.
Audio.cpp is a Voice, TTS & speech project. It focuses on running efficient on-device or local speech AI models without heavy cloud dependencies. Audio.cpp is an open-source project aimed at developers. The project is open source (Open Source). Audio.cpp is available on the web and API.
Behind Audio.cpp is audio-cpp, and it first shipped in 2026. Development happens publicly on GitHub with 1.2k stars and 279 commits in the last 90 days. Key capabilities include GGUF Conversion, text-to-Speech, and Speech Diarization. It exposes integrations via a public API.
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