Layers
Layers captures conversations passively -- no meeting bot required -- and uses AI to extract structured, actionable data. Not just summaries, but budgets, timelines, decision makers, requirements, and pain points.
Getting Started
Use the batch recorder to upload audio files, or start a live streaming session for real-time transcription with speaker diarization.
Once processing completes, review the AI-generated summary, key points, action items, and intake form extraction.
Every meeting shows a transparent cost breakdown -- STT costs, LLM costs, and totals. Monitor your usage on the Usage page.
Features
Upload pre-recorded audio files. Supports WebM, MP3, WAV, M4A up to 100MB.
Real-time transcription with speaker labels using AssemblyAI's streaming API.
Automatic meeting summaries with key points, action items, decisions, and participants.
Structured data extraction: intent, budget, timeline, requirements, pain points, and more.
Per-meeting cost breakdown showing exactly what each API call costs.
Choose your preferred LLM and speech models. See real pricing for each option.
Platforms
Layers runs as a web app (Next.js on Vercel), macOS desktop app (Tauri 2.x with ScreenCaptureKit for system audio), and iOS mobile app (Capacitor 8 WebView) -- all from a single codebase.