Works on any web videoNo files to download, upload or delete
The usual way to turn a video into text is to download the video, upload it to a transcription service, wait, and then remember to delete it. That is impossible for videos you can only stream — a course, a client’s Loom, a webinar replay — and awkward for everything else.
VoxCue works the other way round. It captures the audio of the browser tab you start it on and transcribes it as the video plays. The text builds up beside the player in real time, with a timestamp on every line, and nothing has to leave the page as a file.
Where it works
On YouTube VoxCue can read the video’s existing captions directly, which is instant. Everywhere else — Vimeo, Loom, Coursera, LinkedIn Learning-style course players, news sites and most pages with an HTML5 video — it transcribes the audio live. Because it follows the video as it plays, the transcript covers exactly what you watched.
Turn the text into something useful
Search the transcript for a word and jump to it. Generate an AI overview, takeaways and chapters. Show it as subtitles on top of the video, in the size, colour and position you prefer. Or export it: plain text for documents, SRT or VTT to add captions to your own copy of the video, JSON if you are feeding it into another tool.
Who uses it
- Online learners. Get a written copy of course videos on platforms that offer no transcript.
- Teams. Turn a teammate’s Loom or a recorded demo into notes and action items.
- Accessibility. Read any video with live captions when audio isn’t an option.
- Writers and marketers. Quote webinars and talks accurately, with timestamps to back them up.