AI music generation platform that creates complete songs with vocals, instruments, and lyrics from text prompts in a variety of genres.
High-performance C/C++ port of OpenAI's Whisper speech recognition model. Runs locally with no internet required on CPU, GPU, or Apple Silicon.
Deep learning toolkit for text-to-speech. Train custom voices, clone voices, and generate speech in multiple languages.
Fast, local neural text-to-speech system. Supports dozens of languages and voices, runs entirely offline with low resource usage.
OpenAI's open source speech recognition model. Transcribe and translate audio in 99 languages with state-of-the-art accuracy.
