OpenAI's open-source speech recognition model
Whisper is an MIT-licensed speech recognition model trained on a large multilingual dataset. It transcribes and translates audio in dozens of languages and runs locally on CPU or GPU, with faster community ports such as whisper.cpp and faster-whisper.
OpenAI also serves it through the audio API.
Image Generation
Open-weight image models you can run anywhere
Productivity
Source-available workflow automation with AI nodes
Chatbots
Self-hosted chat UI for local and remote models
Image Generation
Node-based interface for diffusion model workflows
Image Generation
State-of-the-art open image models from Black Forest Labs
Audio
Ultra-realistic text to speech and voice cloning
