100% on your machine. Free to try.
Clearminutes is the AI meeting assistant that records your call, transcribes every word in real time with on-device Whisper, labels who said what, and writes a clean summary with action items the second you stop. Audio never leaves your machine. No cloud, no bot, no upload. Telemetry is off by default: opt in during onboarding only if you want to help. Even then it's anonymous usage stats, never your audio or transcript.
No cloud. No bot. No compromise.
Clearminutes is the local-first AI meeting assistant for people who can't send their calls to someone else's server. Every other tool uploads your audio. Clearminutes runs Whisper transcription and AI summaries locally on your Mac, Windows, or Linux machine. Zero outbound connections during a meeting, verifiable in the in-app privacy monitor. Telemetry is off by default: opt in only if you want to help. Even opted-in, it's anonymous usage stats, never your audio or transcript.
Nothing else.
Clearminutes is the AI meeting assistant that handles the busywork after every call. One click to record. Live transcript as you speak. Clean summary with decisions and action items the second you stop. It lives in your menu bar on macOS or your taskbar on Windows, and stays out of your way the rest of the time.
HIPAA & GDPR-friendly by design.
Clearminutes is the local-first AI meeting assistant built for healthcare, legal, and financial work. It transcribes your calls and writes the summary on your device. Patient and client audio never reaches a server, so you stay inside your HIPAA and GDPR obligations by default.
Runs 100% locally by default · macOS & Windows · No account required to try
No more scrambling for notes. No more chasing who said what. Just clear, structured output from every conversation you have.
Accurate, speaker-attributed transcription powered by an on-device model. No audio leaves your machine: ever. Works fully offline, no internet connection required.
Choose from 20 built-in local models (Gemma, Qwen, Llama, Mistral, Phi & more) or connect your own Ollama instance. Prefer cloud? Bring your own OpenAI, Anthropic, Groq, or OpenRouter key. Text only, never audio.
The AI identifies commitments, tasks, and owners from conversation: and organises them into a checklist you can track or export.
Browse and filter your past meetings by title. Quickly find the call you need from your local archive. Full-text transcript search is coming soon.
Export summaries and action items as PDF or structured outline. More export formats coming soon.
All AI runs on your device by default: no audio ever transmitted. 20 built-in models run with no internet. Connect your own Ollama instance, or bring a cloud API key (OpenAI, Anthropic, Groq, OpenRouter) for enhanced summaries. You choose; we don't.
Real screenshots from Clearminutes running on macOS. Dark mode and light mode supported.
Record your voice right now and watch Whisper transcribe it in your browser. No download, no account, no cloud.
Transcribe your voice in real time. A tiny AI model (~31 MB) downloads once, then runs entirely on your device. Nothing is sent to any server.
Most AI meeting tools send your audio to their servers. Clearminutes is built the other way around: the AI runs on your device, not ours. There's nothing to intercept because nothing is transmitted.
Your microphone audio is captured and processed entirely within Clearminutes on your machine. It is never streamed, uploaded, or buffered to any external server.
20 built-in models (Gemma, Qwen, Llama, Mistral, Phi & more) run entirely on your device with no internet. Connect your own Ollama instance for even more local models. If you optionally enable a cloud provider (OpenAI, Anthropic, Groq, OpenRouter), only the transcript text is sent: never audio.
Transcripts, summaries, and action items are stored in a local database on your machine. You own the files. Optional encrypted cloud sync is available for multi-device access: but it's always opt-in.
We don't ask you to trust us. We remove the need for trust entirely.
Your microphone audio is captured and processed entirely on your device using 20 built-in local models or your own Ollama instance. It is never streamed, uploaded, or buffered to any external server.
Transcription, summarisation, and action item extraction all run without an internet connection. 20 built-in models + your own Ollama instance. No account needed. Just install and start.
We use whisper.cpp, the open-source implementation of OpenAI's Whisper, running locally on your machine. The model weights are public. The code is auditable. No black boxes.
Every release build is scanned by 70+ antivirus engines via VirusTotal.
View report · pendingClearminutes runs quietly in the background. No bots join your call: it listens via your system audio, invisibly.
Words appear live as people speak. Speaker labels are applied afterwards: rename them to match your attendees.
The moment you stop the recording, your AI summary and action items are ready. Review, edit if needed, then export or share.
Start free. Upgrade when you need more. No hidden fees.
Download Clearminutes for free and start your first meeting within minutes. No account required to get started.
All downloads are free. Pro features need a subscription.
"I used to spend 20 minutes after every call writing up notes. Now I just review the summary, tweak anything, and I'm done in 2. It's genuinely useful."
"The action item extraction catches things I said I'd do that I'd already filed as 'probably going to forget'. The accountability alone is worth it."
"Privacy was my main concern. I can't have client calls going to some server somewhere. The local processing model was the deciding factor. That and it actually works."
Your Clearminutes is downloading from our Cloudflare CDN.
Want product updates and tips?
Be among the first to get updates