Transcripts & summaries
How Eavesy processes recordings into a transcript and structured AI summary.
Every recording produces two linked artifacts: the transcript (the complete record of what was said) and the summary (a structured distillation on top of it).
The transcript
- Mac recordings are sealed into recoverable rolling segments and processed as those segments upload.
- Browser recordings upload and process after you stop.
- Supports dozens of languages automatically.
- Copyable and exportable as Markdown.
The transcript is always included on every plan. It’s never paywalled behind a summary-only tier.
The Mac app processes durable audio segments during long recordings, so text can arrive in batches. The browser recorder waits until capture is complete. Eavesy does not currently provide sub-second live captions or speaker diarization.
The summary
After you stop recording and processing finishes, Eavesy generates:
- a title and TL;DR,
- decisions made in the session,
- action items with owners and due dates where mentioned, and
- open questions to follow up on.
It’s structured as clean Markdown, so you can copy the whole brief and paste it straight into Claude, Cursor, or ChatGPT — your agent gets the full context in one shot. More on feeding agents →
Working with the output
Copy or export the Markdown brief and transcript from the completed session. You can edit a brief directly, restore the generated version later, or regenerate it with a built-in format or custom template.
Looking for an old decision across every session? Use semantic search to find a relevant excerpt and open the matching session.