Video to Text: transcript and Essence of a video
Add a video up to 3 GB or a link. You get the transcript with speakers and timecodes, plus the Essence, and a notification when it is ready.
Updated November 2, 20263 min read
Video to Text is for long and heavy files: webinars, lessons, Zoom recordings, YouTube interviews. The video stays next to the text, so you can tap a line and watch that moment.
What you can add
| Source | Limit | Details |
|---|---|---|
| Video file | up to 3 GB | MP4, MOV, WebM, MKV, AVI, MPEG, 3GP, FLV; the web version accepts any video format the browser opens. Before upload the app compresses the video |
| Audio file | up to 100 MB | MP3, M4A, WAV and other common formats |
| Link | up to 2 GB | YouTube, TikTok, Instagram, X, Facebook, Pinterest, direct links; see importing from a link |
| Record video | as for a file | camera, iOS and Android app only |
| Share menu (iOS and Android) | as for a file or link | Video Summary in VocaLingo opens the tool on the Essence tab |
How to get the transcript
Open the Tools tab and tap Video to Text.
Tap Choose, Record video or Paste link.
While the screen shows Compressing video... or Uploading video..., keep the app open and the screen on: the file is still on the way from your phone.
When Recognizing speech... appears, you can close the app. The work continues on the server.
There is no start button and no language choice: recognition starts by itself and detects the language. With a link, the upload stage is skipped because the server downloads the file.
What is on the Video, Text and Essence tabs
Video: the source video with a player. In the app the button is Share video, on the web Download video.
Text: the full transcript with timecodes; when several people talk, it is split into Speaker 1, Speaker 2 and so on and the detected language. Tap a timecode to jump to it in the video. Show timecodes switches to plain text. The text can be copied or shared.
Essence: a short summary with key points, chapters and quotes. It is made automatically right after the transcript, in the language of the app. Export to PDF saves it as a document. Details are in what the video Essence includes.
Under the transcript, What next? offers Discuss in chat, Translate text, Text to speech and Analyze text. The result is saved to the tool's History.
How you find out it is ready
When the transcript and the Essence are ready, VocaLingo sends a push notification. If the push does not arrive, an email comes instead. On iPhone with app version 1.74 or later, progress is shown in a Live Activity on the lock screen.
Push notifications are turned on in Settings, Notifications. If processing takes about 20 minutes or more, the app says recognition is taking longer than usual and the result will appear in History.
How much it costs
The transcript costs about 0.73 tokens per minute, at least 1 token per video: 10 minutes is 8 tokens, an hour is 44. Tokens are taken after the transcript is ready, so a failed job is not charged. The Essence and the PDF are charged separately and cost little: a few tokens even for a long video. All prices are in token prices for each tool.
What Video to Text does not do
It does not put subtitles on the video and does not export SRT. For subtitles use Add Captions.
It does not translate the speech. Use Translate text under the transcript, or Video Translation for a dubbed video.
Speakers are numbered, not named. You cannot rename Speaker 1 in the app.
Without the app
For a link to YouTube, TikTok or Instagram there are pages on the website: video transcript and video summary. They run in the browser and are paid with the same tokens.
If a link does not download or the video does not play, see Video to Text: link or playback problems.
Contact support
Describe the problem and we will reply by email. Add the file name or job ID if you have one.