Open-source benchmark for transcription APIs on meeting audio
Tests Deepgram and AssemblyAI on actual crosstalk instead of clean audiobook samples.

Local Whisper transcription with zero audio egress, Chrome side panel stays invisible.
Remote workers, meeting-heavy teams
Otter.ai · Fireflies · Fathom
Tests Deepgram and AssemblyAI on actual crosstalk instead of clean audiobook samples.
System audio capture avoids bot detection where Otter and Fireflies fail.
No meeting bot to invite; records system audio directly from your browser tab.
CoreML models on Apple Neural Engine beat Whisper.cpp for on-device transcription.
Dual-channel audio capture via PulseAudio is a genuinely useful detail most wrappers miss.
Obsidian-native meeting tool that chains your vault as context for distillation.