Project
Oremi Device
Audio capture service for the Oremi smart home ecosystem with wake word detection, speech transcription, and Home Assistant integration via MQTT.
115 commits 1 contributor Updated Sep 2026
Overview
Oremi Device captures microphone audio and connects it to Oremi services:
- Oremi Ohunerin detects wake words and environmental sounds.
- Oremi Andika transcribes speech after Ohunerin detects a wake word.
- Oremi Izwi or an OpenAI-compatible Edge-TTS server synthesizes spoken NLP responses when configured.
- MQTT exposes events, device controls, availability, and Home Assistant discovery entities.
The application monitors audio hardware while it runs. It can switch to another compatible microphone when the active device disappears and switch back when a preferred device becomes available again.
Repository (opens in a new tab)
Documentation (opens in a new tab)
Contribution (opens in a new tab)
Technology
- audio
- home-assistant
- microphone
- mqtt
- oremi
- pyaudio
- Python
- smart-home
- speech-to-text
- stt
- transcription
- voice-assistant
- wakeword
Repository information
- Primary language
- Python
- Created
- June 19, 2026
- Last activity
- September 20, 2026
Activity
Daily commits on the default branch, across the whole project history.
Mon
Wed
Fri
