EdgeNote AI Documentation

On-device speech-to-text transcription and AI summarization for meetings, lectures, and conversations.

What is EdgeNote AI?

EdgeNote AI is a desktop application that transforms your audio recordings into actionable insights. Record meetings, lectures, or conversations, and let AI automatically transcribe and summarize the content - all processed locally on your device for complete privacy.

100% Private
All processing happens on your device. Your recordings never leave your computer.
GPU Accelerated
Leverages Metal (macOS) or CUDA/Vulkan (Windows) for fast transcription and summarization.
AI-Powered
Extracts action items, decisions, goals, and key points automatically from your conversations.

Quick Links

Getting Started
Install EdgeNote AI and record your first meeting in minutes.
  • Download & install
  • Configure models
  • Start recording
System Requirements
Check if your device supports EdgeNote AI and which features are available.
  • macOS & Windows
  • RAM requirements
  • GPU acceleration
Features Overview
Explore all the features EdgeNote AI offers for recording and transcription.
  • Recording & import
  • Transcription
  • AI summarization
Recording Workflow
Understand the complete flow from recording to actionable insights.
  • Recording
  • Transcription
  • Summarization

Core Capabilities

Recording - Capture microphone and system audio simultaneously. Auto-detect meetings from Zoom, Teams, Slack, and Google Meet.
Transcription - Convert speech to text using Whisper models with GPU acceleration. Supports 99 languages with speaker diarization.
AI Summarization - Extract key points, action items, decisions, and goals using local LLM models like Qwen, DeepSeek, Phi, and Llama.
Speaker Management - Identify and track speakers across recordings. Visualize speaker relationships with interactive graphs.
Organization - Group recordings into collections, add tags, search across all content, and export or share summaries.