Video Essence: what the summary includes and costs
The Essence is written automatically right after the transcript and charged at that moment: brief, key points, chapters with timecodes, quotes and PDF export.
Updated November 2, 20263 min read
The Essence is the third tab in Video to Text. The same tab exists in Text Transcription and Audio Translation. It tells you what the video is about without watching it, and its timecodes take you to the right moment.
When the Essence is made and charged
Video to Text writes the Essence on the server right after the transcript, before it sends the "ready" notification. The Essence is charged at that moment, whether or not you open the tab. It cannot be turned off.
If writing the Essence failed, the tab shows "Failed to summarize" and a Try again button. A finished Essence cannot be regenerated: there is no button for it.
What the Essence includes
The Essence has up to three sub-tabs. A sub-tab appears only when the video has something for it, so a 20-second clip often has just Brief.
| Sub-tab | What is inside |
|---|---|
| Brief | a title, a summary, quotes from the video and the main takeaway. If a quote is translated, the original wording is shown under it |
| Key points | the main points with timecodes. For a tutorial the sub-tab is called Steps. Below them, when the video has them: Questions and answers, Terms, Action items |
| Chapters | the video split into parts with a timecode for each |
Tap a timecode in Key points or Chapters to play the video from there. If the speech was hard to make out, Brief starts with "The speech is hard to make out, so the essence may be incomplete."
What language the Essence is in
The Essence is written in the language of the app, even if the video is in another language. That makes it a quick way to understand a video in a language you do not speak. For an Essence in a different language, change App Language in Settings before you add the video.
How to save the Essence as PDF
Tap Export to PDF on the Essence tab. The document contains the Essence and a mind map of the video's topics. Building the mind map costs a small amount of tokens. In the app the file opens in the share menu, on the web it downloads.
To copy just one part, open its sub-tab and use the copy button under it.
How much the Essence costs
The Essence is charged separately from the transcript: a fraction of a token for a short clip and a few tokens for an hour-long video. The transcript itself costs about 0.73 tokens per minute, so an hour of video with the Essence comes to roughly 45 to 50 tokens. Details are in token prices for each tool.
Essence in the browser, without the app
For a YouTube, TikTok or Instagram link there is the video summarizer page on the website. Paste the link, pay with tokens (a token pack can be bought right there) and get the same Essence with PDF export and a link to share. There is no free run.
Frequently asked questions
Can I get only the Essence, without the transcript?
No. The Essence is written from the transcript, so Video to Text always makes both and charges for both.
Why does a short video have no chapters or quotes?
The Essence adapts to the video. A song or a 30-second clip has little to split into chapters, so only Brief is shown. Long lectures and interviews get all three sub-tabs.
Contact support
Describe the problem and we will reply by email. Add the file name or job ID if you have one.