Rhasspy
Rhasspy 3 is an early developer-preview voice assistant toolkit with Home Assistant integration and an MIT license. Archived and unmaintained.
Rhasspy 3 is an early developer-preview local voice assistant toolkit for developers building their own assistants or adding voice control to Home Assistant. The project is archived and no longer maintained. It keeps data on your computer unless you choose to send it elsewhere, and its speech components support languages beyond English.
The toolkit connects microphone input to spoken responses, with wake word detection, speech recognition, intent handling and speech synthesis. You can choose different engines for individual parts of that voice loop rather than commit to a single speech backend. Supported transcription engines include Whisper, whisper-cpp, faster-whisper and Vosk; speech output options include Piper, Mimic 3 and eSpeak NG.
Home Assistant handles commands through its conversation integration, and Rhasspy supports satellite devices for audio input and output. Its Python code is open source under the MIT license. The Wyoming protocol connects separate speech programs, while adapters let developers bring other programs into the same system. HTTP and WebSocket APIs expose transcription, speech synthesis and audio streaming to other applications.
This is a toolkit that needs development work: it lacks a user-friendly web interface and automated setup for speech programs and models. Intent handling is limited to Home Assistant, custom speech recognition grammars aren't supported, and the voice pipeline doesn't retain conversational context.
