Features

AI chat lets you ask questions about your transcription in plain language — perfect for long meetings, interviews, or lectures where you don't want to re-read the whole thing. Open any transcription and you'll see a chat panel next to the text.

Ask things like "What were the action items?", "Did anyone mention the Q3 budget?", or "Summarize the disagreement between Speaker 1 and Speaker 2." The AI uses only your transcription as context, so answers are grounded in what was actually said. Chat history is saved per transcription so you can come back to it later.

The AI summary turns a long transcription into a short, structured recap — typically a paragraph of context, a bulleted list of key points or action items, and (where relevant) a list of speakers and their main contributions.

Click Generate Summary on any completed transcription. We'll process it in a few seconds and the result is saved alongside the full text. Summaries are great for meeting notes, interview highlights, lecture review, and podcast show-notes drafts. You can regenerate the summary anytime if you want a different style.

Open the transcription, click the Download button, and pick SRT. SRT is the standard subtitle format — it includes timestamps so each line of text appears at the right moment in your video.

Use SRT for YouTube (upload the file as a subtitle track), Vimeo, or any video editor like Premiere, Final Cut, or DaVinci Resolve. SRT works best on transcriptions with reasonably short sentence segments — long monologues are still valid SRT but harder to read as subtitles.

Open any transcription, click Download, and pick the format you want:

• TXT — plain text, no formatting, perfect for copy-paste into other tools.
• DOC — Microsoft Word format with basic formatting, ready to edit.
• PDF — printable PDF with page numbers, good for archiving or sharing.
• SRT — subtitle format with timestamps (see How do I download a transcription as SRT?).

All four formats are generated on demand from the same transcription, so you can download multiple formats of the same file as many times as you want.

Speaker diarization (also called speaker identification) automatically detects and labels different speakers in your audio. Each speaker gets a label — Speaker 1, Speaker 2, etc. — so you can follow who said what.

Enable it on the upload form by setting Identify Speakers to Yes. It's available on every plan, including Free. Diarization works best with clear voices recorded with separate microphones (or speakers physically apart in the room). Overlapping speech or speakers with very similar voices may occasionally be merged, but we get most multi-speaker conversations right.

We've got you covered — when you upgrade from Free to Pro or Business, we automatically reprocess any trimmed transcriptions with the full original audio. You don't need to do anything.

Reprocessing happens in the background within a few minutes of your upgrade. The next time you open the trimmed transcription, you'll see the full text. The original audio is kept for 24 hours, so as long as you upgrade within that window, the reprocess works seamlessly. After 24 hours, the original audio is deleted and reprocessing isn't possible.

The usage card on your dashboard shows three things at a glance: how many hours you've used this month, how many you have left, and when your quota resets.

You'll see a progress bar that fills up as you use your monthly hours, plus a clear breakdown — for example, "3.2 / 10 hours used, 6.8 hours remaining, resets May 15." If you're approaching your limit, we'll show a warning banner so you can upgrade or buy extra hours before your next file gets trimmed.

Yes — your dashboard has a search box at the top that searches across the full text of every transcription you've made, plus titles and metadata.

Search is fast and supports partial matches, so typing budget will find every transcription where someone mentioned a budget. Combine search with the filters next to it to narrow by language, speaker identification on/off, duration, or date. Hit the X to clear and see everything again.

Right now, transcriptions are private to your account — there's no built-in share link. To share, download the transcription as PDF, DOC, or TXT and send it via email or your usual file-sharing tool.

We're considering shareable links and team workspaces for a future release. If that would help your workflow, drop us a line at [email protected] — we read every message and product feedback shapes what ships next.