Convert video to text, without extracting the audio
Tutorials, call recordings, video courses, social media content: the speech in a video becomes a readable, searchable document with a single upload. No converters, no intermediate steps: the video file goes in as-is and clean text comes out.
How it works — in 3 steps.
Upload the video file
Drag in the video in its original format and Verlio takes care of the rest, whatever the length. If the content is split across several clips, you can merge them into one final document.
The AI isolates the speech and transcribes it
Voices are recognized and attributed, up to 8 and more people, and AI cleanup fixes typos and terminology. Got the slides shown in the video? Attach them as context and the terms come out exact.
Export a document or subtitles
Download the text as Word or PDF, or the subtitles as SRT and VTT if the video is going back online. The Structured Document adds a summary, key points and sections for anyone who just needs the gist.
Which videos you can transcribe
Anything containing speech: the demo recorded for a client, the video course you bought and never finished, the testimonial filmed for the website, the saved livestream, the screencast with the software walkthrough. If the file is on your computer, it can be transcribed.
Only the length of the speech matters, not the size of the file: a high-definition video and a compressed audio file of the same duration use the same credits. Long files — like the full recording of a training day — go through in a single upload.
From video to article: content that gets reused
A twenty-minute video contains an almost-finished blog post: the transcript is the draft, and the Structured Document supplies section headings, key points and a summary for the preview. You already did the creative work by speaking; only the polish remains.
For teams, transcription finally makes videos searchable: the answer given at minute 47 of Thursday's recording is found with a text search, not by rewatching an hour of footage at double speed.
What it costs, concretely
Billing is by duration: 1 credit per 30 minutes of video, with packs starting at €5 and no subscription. A two-hour video costs 4 credits; a clip under 10 minutes costs nothing.
To judge the quality on your real material there's 1 hour of free trial at signup, no card required: you upload an actual video and evaluate the result, not a canned demo.
Frequently asked questions.
Do I have to convert the video to MP3 before uploading?
No — that's the point: the video is uploaded in its original format and the speech is extracted internally.
Can I transcribe a two-hour video?
Yes, long files are supported: two hours equal 4 credits. There's no need to split the video into parts.
Several people speak in the video: are they told apart?
Yes, each voice is labeled separately, up to 8 and more speakers: useful for recorded panels and video interviews.
Can I get subtitles as well as the text?
Yes, from the same upload you also export synchronized SRT and VTT, alongside Word and PDF.
The video is in another language: can I get the document in English?
Yes, set English as the output language and receive the text directly in your language, from the 35+ supported.
You might also need.
Try it on your own file, right now.
Upload an audio or video file, choose the document language and download the result as Word or PDF. Your first hour is free and we never ask for a card.