A summary needs a transcript under it
Nothing useful gets summarized from audio alone. WhipScribe transcribes the recording — one file up to 5 GB and up to 12 hours, in 99 languages detected automatically — and the summary is written from that text.
That order matters for you, not just for the machine: when a line in the summary looks wrong, you can go to the quote and the timestamp it came from and read the surrounding words.
What the summary is made of
An overview that says what the recording was. The takeaways, as points rather than prose. Chapters, so a long recording has a shape you can skim. And key quotes, each one carrying the timestamp it sits at.
Quotes stay in the language of the recording. A Spanish interview yields Spanish quotes.
Ask it your own questions
The generated summary answers the obvious questions. The ones specific to your work usually are not obvious, so there is a chat over the transcript: ask what was said about pricing, or where a decision was made, and it answers from the recording.
Every transcript and its summary stay in a searchable Library, so you can come back to a recording weeks later.
Getting the text out
Export as TXT, SRT, VTT, DOCX or JSON. The transcript is yours to move into whatever you write in.
Transcripts are never used to train AI.
What it costs
The first transcript is free at any length, no card and no account needed to start. The second is $0.99, once per email address.
After that: $8 / 1,000 minutes, $12 / 2,000 minutes, $24 / 5,000 minutes, one-time, no subscription, and the minutes do not expire. Workspace is $19/month for unlimited transcription on the web app.
How to do it
- Upload the recording, paste a public link to it, or record in the browser.
- Wait for the transcript — usually about two minutes per hour of audio.
- Open the overview and takeaways, then skim the chapters.
- Check a claim against the key quote and the timestamp it sits at.
- Ask the chat anything the summary did not cover.
- Export as TXT, SRT, VTT, DOCX or JSON.