Hi all, I maintain an open-source project called StenoAI. I’m happy to answer questions or go deep on architecture, model choices, and trade-offs as a way of giving back.
What is StenoAI
StenoAI is a privacy-first AI meeting notetaker trusted by teams at AWS, Deliveroo, and Tesco. No bots join your calls, there are no meeting limits, and your data stays on your device. StenoAI is perfect for industries where privacy isn't optional - government, healthcare, defence & finance/legal.
What makes StenoAI different
- Fully local transcription + summarisation keeping your data private. We really focus on summarisation quality using local models.
- Ask StenoAI feature - chat with your meeting transcripts
- Multi-Language Support - Supports up to 10 most commonly spoken languages - English, German, Spanish, Portuguese, French, Arabic, Hindi, Japanese, Chinese & Korean. 2 more than Granola!
- supports larger models (7B+) than most Open Source options, we don't limit to upsell
- Remote Ollama Server Support - run your your own models on a Mac mini or private server on network and connect directly with StenoAI (great for enterprise users)
- strong UX: folders, search, Google & Outlook Calendar integration
- Cloud API Support (Not recommended) - OpenAI, Anthropic and OpenAI comaptible APIs Supported
- StenoAI Med for private structured clinical notes is on the way
If this sounds interesting and you’d like to shape the direction, suggest ideas, or contribute, we’d love to have you involved. We have an active community and continuously growing. Thank you :)
GitHub: https://github.com/ruzin/stenoai
Discord: https://discord.com/invite/DZ6vcQnxxu
Top comments (8)
Are you planning to develop also a version for Linux ?
hey absolutely! if you are on linux, and you'd like to drive the roadmap or help with testing, that'd be great. Please join discord - discord.com/invite/DZ6vcQnxxu
Well I don't use discord for privacy reasons they violate. Collaborating with Persona and Palantir, sorry no sorry dude.
The "Remote Ollama Server" feature caught my eye. I run a Mac Mini (M-series, 64GB) as a 24/7 AI agent host — Ollama serves qwen3:30b and deepseek-r1:70b locally, and having meeting transcription pull from the same local inference server would be a clean topology.
Two questions from an actual local-first practitioner:
Model selection for summarization — you mention supporting 7B+ models. Which architectures have you found produce the best meeting summaries? I'd imagine instruction-tuned models (like Qwen or Mistral) outperform base models significantly here, but the "structured clinical notes" use case (StenoAI Med) must have very different requirements from a casual standup summary.
Transcript drift in long meetings — Whisper-based transcription tends to accumulate errors over 60+ minute sessions (speaker confusion, repeated phrases, timestamp drift). Do you do any post-processing correction, or is the raw Whisper output the canonical transcript?
The privacy angle resonates — I built a browser-only finance tool where all data stays in IndexedDB specifically because financial data + cloud = trust barrier. Same principle applies even more strongly to meeting recordings.
@maxxmini great questions.
Remote Ollama - Yes, we had some enterprise users start to use this feature. Atm, it allows our roster of models but we quickly (likely today) will allow support of any ollama models you are running. We are advising users to go with 30b qwen as well.
Model selection - So what I've found is that my model selection is less important post 7b mark, and it's more the prompt engineering and extraction strategies. There is still work to be done here.
StenoAI Med - I started to test StenoAI Med, it is going to live within the product and be activated by a toggle within advanced that will swap out summary templates and branding. It is essentially StenoAI under the hood but with more hardened controls and med specific models.
Transcript Drift - We used the smallest whisper model for performance reasons and we don't have diarisation yet. Post processing correction is interesting, could you elaborate?
We'd be happy for you to try the product, we recently had a German govt department buy Mac minis as they were happy with StenoAI :) W'd be even happier if you joined our discord and started feeding back on the roadmap, its privacy aware users like yourselves that are really helping us driving great features. discord.com/invite/DZ6vcQnxxu
Thank you for writing this.
Some comments may only be visible to logged-in visitors. Sign in to view all comments.