Windows Port · Python + PySide6

Your meeting assistant.
Fully on your machine.

Transcribes both sides of a call in real time, surfaces relevant notes from your knowledge base as you speak, and writes session summaries when you're done. No data leaves your computer.

WinOpenOats — Weekly Standup
Live Transcript
Them So the Q3 plan is looking strong — we're targeting 15% growth and the roadmap is mostly locked...
You Right, and what about the timeline for the migration?
Them
💡 From notes
Q3 Roadmap
updated 2 days ago
Migration Plan v2
last week
Growth Targets
3 weeks ago
Mic + system audio via WASAPI
Works with Ollama locally
Windows 10 / 11
Free & open source
Based on OpenOats

Features

Everything you need
in every meeting

🎙

Real-Time Transcription

Captures mic and system audio simultaneously via Windows WASAPI. Both sides of the conversation transcribed as you speak, with speaker labels.

💡

Live Knowledge Base Suggestions

While the meeting runs, WinOpenOats searches your notes and surfaces the most relevant documents — you always have the right context on hand.

📝

Auto-Generated Session Notes

When the session ends, an LLM summarizes the transcript into structured notes automatically. Past sessions are saved and browsable.

🔒

Fully Local Mode

Use Ollama for LLM + embeddings and Whisper or Parakeet for transcription. Nothing leaves your machine — optionally zero cloud APIs required.

🛡

Your conversations stay on your machine

WinOpenOats optionally operates entirely offline. Choose Ollama for the language model, Whisper or Parakeet for transcription, and local embeddings — no API keys, no data sent anywhere. Screen share protection via Windows SetWindowDisplayAffinity keeps the assistant hidden from screen recordings.

Transcription Models

Pick the right model
for your hardware

Model Size Notes
Parakeet TDT v2 ~600 MB English, fast, NeMo backend
Parakeet TDT 1.1B ~1.1 GB Multilingual, NeMo backend
Whisper Base ~142 MB Good for low-resource machines
Whisper Small ~244 MB Balanced speed / accuracy
Whisper Large v3 Turbo Recommended ~800 MB Best accuracy / speed balance
Whisper Large v3 ~1.5 GB Maximum accuracy

Setup

Running in three steps

01

Clone & install

Requires Python 3.12 and a microphone. Run the onboarding wizard to pick your model and configure API keys.

git clone https://github.com/
ibrahimokdadov/winopenoats
cd winopenoats
pip install -r requirements.txt
python main.py
02

Choose cloud or local

For cloud mode: add your OpenRouter API key for LLM and Voyage AI key for embeddings in Settings. For fully local mode: install Ollama and pick local models — no keys needed.

# local mode — no API keys
ollama pull llama3.2
ollama pull nomic-embed-text
# then select in Settings → LLM
03

Add your notes

Drop Markdown files into your knowledge base directory. WinOpenOats indexes them and will surface the most relevant ones during every call.

# knowledge base location
~/.winopenoats/knowledge/

# supports: .md, .txt

Never lose context
in a meeting again.

Free, open source. Windows 10/11. Python 3.12.