Settings are saved locally in your browser.

System audio device is configured via --device at server startup.

Engine for "Speak context" mic button

Whisper runs on your server — better for technical terms. Browser uses built-in speech recognition.

How often new transcript is sent to Claude for concept extraction.

Segments carried over between extraction windows to catch boundary topics.

Seconds an Incoming card stays visible before auto-expiring to History.

Setting an explicit language improves accuracy, especially with accented speech. Use "Auto-detect" for multilingual meetings.

Help improve Ori by sharing anonymous usage counts and timing data. Analytics never includes meeting content, audio, transcripts, or extracted terms.

Go to your AI provider, create an API key, copy and paste it here. ORi securely stores your encrypted key in a Cloud Vault where it is not exposed to the weaknesses of a browser. Read the full guide or ask the Help Chatbot.