Memory Notch
CLOUD SCRIBES
Memory Notch vs Otter.ai
The best-known meeting transcriber, with a bot that joins the call.
| Memory Notch | Otter.ai | |
|---|---|---|
| Where the audio goes | Nowhere | To Otter's servers |
| Processing | On the Neural Engine | Cloud |
| Bot in the call | No | Yes, a participant joins the meeting |
| Speaker labels | Yes, on-device | Yes, in the cloud |
| Platform | macOS 26 | Web, iOS, Android, Chrome extension |
| Open source | No | No |
| Price | Not released yet | Pro $16.99/month, Business $30/user/month |
Details checked September 2026 against Otter.ai's own documentation. Prices move; treat the figure as a starting point, not a quote.
What Otter.ai does well
- Real-time transcription with a searchable archive going back years.
- Shared workspaces, comments and assigned action items across a team.
- Integrates with Zoom, Teams, Meet and Slack out of the box.
What it costs you
- The audio and the transcript live on Otter's infrastructure.
- The bot is visible in the participant list, which changes how people talk.
- Nothing works without a connection.
Where Memory Notch is different
Memory Notch does the transcription and the speaker separation on your Mac's Neural Engine. There is no account, no telemetry and no API key, and a recording is never sent anywhere. The models download once, and after that a recording transcribes with the network off. Each one becomes a directory of plain Markdown in ~/memory, which means the AI tool you already use can read it by path: no MCP server, no export step, no API.
It is also a smaller thing than Otter.ai. One Mac, one person, no team workspace and no integrations. If you need a shared archive or a CRM, Otter.ai is the better tool and this page is not trying to talk you out of it.