Skip to content
Summo

Pricing

Today there is exactly one thing to pay: nothing. The full application is open source and free, with no limits. The two below are the sync service — not built yet, not for sale, and listed here so you know in advance what would ever cost money and what never will.

Free

$0

forever, open source

  • Unlimited recording and transcription
  • Speaker attribution
  • Translation into 46 languages, on-device
  • Export to TXT, MD, SRT, VTT, CSV, JSON
  • Bring your own LLM key
  • No account
Download
Not yet

Sync

—

end-to-end encrypted, across your devices

  • Sync between your own machines
  • Voice profiles reused across meetings
  • The server cannot read the contents
Tell me when it exists
Not yet

Team

—

for organisations

  • Shared workspace and roles
  • Retention policy set by an admin
  • Self-hosting and a commercial licence
Get in touch

We do not sell accuracy. On a slower machine Summo suggests a smaller model — the accuracy changes because of your hardware, not because of what you paid. Recognition and diarisation will stay free and stay local.

Thirty seconds is enough to tell

Install it like anything else. The first time it opens, Summo measures your machine and suggests a model — and records nothing until you press record.

Version 0.38.1, released 28 September 2026 · see every download

No window needed?

The command-line build is one binary: run summo serve and open a browser. It is also the only build for Linux on ARM, and for a machine with no desktop at all.

Command-line builds and checksums

On macOS, the first time

macOS shows a dialog with two buttons — Move to Trash and Done. Nothing is wrong with the app: the signature is valid, there is simply no Apple certificate behind it ($99 a year). Press Done, then open Privacy & Security, scroll to the bottom and press Open Anyway. Once, and never again.

Or, if you would rather type:

xattr -dr com.apple.quarantine /Applications/Summo.app

Every download has a .sha256 beside it — check it first if you are careful.

Installed? Open it in English

Summo opens in whatever language your computer is set to. If yours is set to something else and you want the interface in English, press this after installing — once is enough.

Open Summo in English

It applies to the first run only, and never overrides a language you picked yourself. Change it any time in Settings.

Download it and record one meeting

Free, open source, no account. If it does not suit you, deleting one folder is the whole uninstall.

macOS on Apple Silicon · Windows x64 · Linux x64 and arm64. Android is on the way.

Questions people ask

"The audio never leaves" — how would I check that?

Three ways. One: the source is open, recognition lives in crates/summo-asr, and there is no HTTP client in it. Two: unplug the network and record — everything still works. Three: firewall the app and the transcript is unchanged. Only summarising and answering questions need the network, and the settings screen states whether the endpoint you chose is local or remote.

Does a bot have to join the call?

No. Summo captures your microphone and your system audio directly, so it works with Zoom, Meet, Teams, a phone call, or people in a room — anything your machine can hear.

How accurate is Vietnamese?

2.4% WER on Fleurs VI with the gipformer-65M model. But Fleurs is clear read speech; a real meeting is much harder, and we have not published a number for real meetings because there is no hand transcript to check against yet. When there is, it will sit beside this one.

Does translation run locally?

Yes. As of this version, translation into 46 languages runs on a model inside the app — no Ollama, no network. Only summarising and question-answering call a language model, and you choose that endpoint.

What if my machine is slow?

On first launch Summo measures it for fifteen seconds and picks a pair of models to match. The default Vietnamese model is 73 MB and runs 9× faster than realtime on four CPU cores — no GPU.

Where is my data?

A folder of Markdown in your application data directory. Open it in Obsidian, grep it, put it in git. Audio is stored as Opus and deleted after 30 days by default while the transcript is kept — both configurable.

How can it be AGPL and still be a business?

The app and the core are AGPL-3.0, so nobody can take it and run a closed service on it. What would be paid for later is the sync service, which lives in its own repository and is not needed to run the app. A company that needs to be free of the AGPL buys a commercial licence.