Skip to content

About

macOS meeting recorder — mic + system audio, WhisperKit transcription, LLM summaries (Claude/Gemini/OpenAI/Ollama)

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

MacMeetSubscriber (Meeting Recorder)

macOS app that records meetings (microphone + system audio via ScreenCaptureKit), transcribes them with WhisperKit, and summarizes with a configurable LLM provider (Claude / Gemini / OpenAI / local Ollama).

Author: Alex Pavlyuk (@Alex-Pavlyuk)

Build

cd MeetingRecorder
./build_app.sh
open dist/MacMeetSubscriber.app

The first build signs the app to establish TCC identity. Subsequent builds only replace the binary (preserving mic / screen capture permissions).

Settings overview

Open the app → Settings.

  • LLM Provider — pick Claude / Gemini / OpenAI / Ollama
  • API keys — per-provider, stored in macOS UserDefaults
  • Ollama URL — default http://localhost:11434
  • Ollama model — auto-discovered from the running Ollama instance
  • Context window (num_ctx) — see the memory section below
  • Whisper model — small (multilingual, recommended) or tiny (fast)
  • Use multi-stage pipeline — see pipeline section
  • Auto-summarize after recording — run transcription + summarization automatically after Stop

Workflow

  1. Start Recording → mic and system audio are captured to mic.wav / system.wav
  2. Stop Recording → app transcribes with WhisperKit (multi-pass language detection) and produces transcript.md
  3. If auto-summarize is on, the summarizer runs and writes summary.md
  4. Each recording lives under ~/Documents/MeetingRecorder/YYYY-MM-DD_HH-MM-SS/

You can also re-summarize existing recordings: right-click the row or use Summarize Last / Summarize All Pending.

Ollama context window and memory

The KV cache grows linearly with num_ctx. Pick the smallest value that still fits your meetings — larger contexts need more RAM and slow down prefill.

Rules of thumb

40-minute meeting ≈ 18-22K tokens of transcript. It will only fit completely when num_ctx ≥ 32768.

Meeting length Recommended num_ctx
≤ 15 min 8192
15 – 25 min 16384
25 – 55 min 32768 ← most common
55 min – 1.5 h 65536

RAM footprint (8-9B models, Q4)

num_ctx KV cache Model Total in RAM
4096 ~0.5 GB ~5 GB ~5.5 GB
8192 ~1 GB ~5 GB ~6 GB
16384 ~2 GB ~5 GB ~7-8 GB
32768 ~4 GB ~5 GB ~9-10 GB
65536 ~8 GB ~5 GB ~13-14 GB

For 12B models (gemma3) add ~2-3 GB.

Troubleshooting slow generation

Symptom: tok/s is 10× lower than expected (e.g. 2-3 tok/s on an 8B model that should run at 20-30 tok/s on Apple Silicon).

Almost always the cause is memory pressure: several Ollama models loaded at once, causing swap. Check:

# Show currently loaded models and their size:
curl -s http://localhost:11434/api/ps | python3 -m json.tool

# Show swap activity; if Swapouts is growing, you're thrashing:
vm_stat | grep -E "free|Swapouts"

Fix:

# Unload every model except the one you want:
for m in qwen3:8b qwen2.5:7b llama3.1:8b gemma3:12b deepseek-r1:8b mistral-nemo; do
  curl -s http://localhost:11434/api/generate -d "{\"model\":\"$m\",\"keep_alive\":0}" > /dev/null
done

# Prevent this from happening again — put this in ~/.zshrc or your LaunchAgent:
export OLLAMA_MAX_LOADED_MODELS=1

# If Ollama has been running for days, restart it:
brew services restart ollama

# Keep Ollama up to date — older 0.20.x releases have Metal regressions:
brew upgrade ollama

Other causes of slow generation:

  • Thermal throttling (common on MacBook Air / base M2 under sustained load — let it cool down)
  • Other apps holding wired memory — close Chrome / Docker / Xcode if tight on RAM
  • Model running on CPU (unusual). Check size_vram in /api/ps — should equal model size

Multi-stage pipeline

Settings → Summarization → Use multi-stage pipeline switches from a single LLM call to a 6-stage process:

  1. Chunk the transcript into 5-minute windows (no LLM)
  2. Extract structured JSON (topics, points, decisions, action items) per chunk — N LLM calls with JSON format
  3. Cluster chunks by normalized topic name (no LLM)
  4. Write a themed section per cluster — K LLM calls
  5. Consolidate action items across chunks — 1 LLM call
  6. Overview — 1 LLM call

When to use it

Good fit:

  • Cloud providers (Claude / OpenAI / Gemini) — extra calls are cheap, quality jumps noticeably
  • Local Ollama only if generation speed ≥ 15 tok/s (see troubleshooting above)
  • Long meetings (1+ hour) where single-shot can't hold the full transcript in context

Bad fit:

  • Slow local inference (<10 tok/s) — each chunk takes many minutes, overall time balloons to 40+ min
  • Short meetings (<15 min) — single-shot already fits everything

Expected timings (40-min meeting, 9 chunks)

Setup Single-shot Pipeline
Claude Sonnet ~20 s ~40-60 s
Ollama @ 25 tok/s ~8 min ~10-12 min
Ollama @ 15 tok/s ~15 min ~18-22 min
Ollama @ 3 tok/s (thrashing) ~40 min don't

Pipeline eliminates most date/fact hallucinations because each chunk sees only a small slice of transcript, so the model can't invent things that weren't said.

Files written per recording

~/Documents/MeetingRecorder/2026-04-16_15-33-19/
  mic.wav               # microphone capture
  system.wav            # system audio capture
  transcript.md         # speaker-labeled, timestamped transcript
  summary.md            # LLM summary
  metadata.json         # duration, segment count, languages, provider, status

metadata.json.status is one of pending_summary (transcribed but not summarized) or complete.

License

Copyright © 2026 Alex Pavlyuk.

Licensed under the Apache License, Version 2.0 — see LICENSE.

About

macOS meeting recorder — mic + system audio, WhisperKit transcription, LLM summaries (Claude/Gemini/OpenAI/Ollama)

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages