Projects.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

🎥 Command line media player

GUI for a Vocal Remover that uses Deep Neural Networks.

Mixxx is Free DJ software that gives you everything you need to perform live mixes.

An audio server, programming language, and IDE for sound synthesis and algorithmic composition.

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.

Bare-Metal Rust Audio AI Framework

Native PHP extension binding the FFmpeg libraries (libavformat, libavcodec, …) in pure C against the Zend API — open, probe, and transcode media with an object-oriented API and typed exceptions. An Artisan Build project.