SEPIA-Framework/sepia-docs

Documentation and Wiki for SEPIA. Please post your questions and bug-reports here in the issues section! Thank you :-)

24
/ 100
Experimental

SEPIA is a modular, self-hosted voice assistant framework built on a Java server with Elasticsearch backend and JavaScript clients, supporting voice, text, and touch interactions across browsers, Android, and Raspberry Pi devices. The architecture decouples speech recognition (via pluggable STT server using Kaldi/Vosk) from the core assist-server, which handles NLU, intent recognition, dialog management, and service orchestration through a REST API. It includes pre-built smart-services (news, smart home via openHAB, timers, lists, weather) and provides extensibility through a Java SDK and integrated code editor for custom service development.

251 stars. No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 1 / 25
Community 13 / 25

How are scores calculated?

Stars

251

Forks

18

Language

License

Last pushed

Nov 24, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/SEPIA-Framework/sepia-docs"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.