Video to text with private AI
Open a video and turn its spoken audio into editable text with Whisper AI in this browser. The video and its audio stay on your device.
- Transcribed on your device
- 99 languages
- Word, PDF, SRT, VTT
- Free to use
This recording
Saved to your account
- Source
- Length
- Windows
- Engine
- Checked when the model starts
- Language
- Not known until it is transcribed
This transcript came from your account; the audio stays wherever you keep it.
Changing a setting transcribes again and replaces your edits.
Long recordings run best on a computer: a phone is slower and can run out of memory.
Keeping stores this recording in this browser until you delete it. Anyone using this device can play it.
The time remaining appears after the first 30-second window.
Marked passages
Marks become an index at the front of the PDF, with the page and line each one landed on.
Subtitles No transcript yet
Document Numbered lines · a timestamp on every line · US Letter
Saving keeps the text, times, speaker labels and marks in your account. Your audio is not uploaded.
Signing in reloads the page, then saves this transcript. Open the recording again afterwards unless it is kept here.
Kept on this device
Nothing is kept on this device. A recording is kept only when you press “Keep on this device”.
These stay in this browser until you delete them, and anyone using this device can play them.
A private AI video transcriber
Quiet Transcript reads the audio track of a video your browser can decode and uses Whisper AI to produce an editable, timestamped transcript. It does not analyse the pictures.
MP4 and WebM support depends on your browser. A meeting recording saved as an MP4 transcribes the same way.
What happens to a video you open
On this route the file picker is set to accept video as well as audio. Choose a clip from your disk and the browser reads it where it sits. The tool takes the audio track out of the container and sets the picture aside.
That audio is converted to the 16 kHz mono sound the model is given, and Whisper transcribes it in 30-second windows. The video itself is never uploaded, and the tool does not look at a single frame.
When the transcript is ready, play the video's sound beside it. Each line has a time. You can jump from a sentence on screen to the same moment in the recording and decide whether the words are right.
Which videos work, and which do not
Which containers open depends on your browser, not on this site. The tool asks the browser as the page loads and lists what it reads under Which files open here? MP4 and WebM are the usual ones.
If the browser cannot decode a file, it says so, and another browser may open the same file. Converting the recording to MP3 or WAV is the reliable way round the problem.
A video with pictures and no sound track is not damaged, and there is no speech in it to find. For an MP4, the tool tells you so instead of returning an empty transcript. Screen recordings made with the microphone switched off are often like this.
On a computer a file may be up to 2 GB. On a phone, shorter videos work best, because a phone has less memory to hold the sound while the model reads it.
Where a video transcript is useful
A recorded call. A call recording saved as MP4 or WebM opens here if your browser can read it. You get the spoken part as text you can search, with a time on every line.
A lecture or webinar. Read the transcript, find the passage you need, and press its time to hear it. This is faster than scrubbing through the video for a phrase you half remember.
A clip you want to quote. Correct the lines you intend to use against the recording before they go anywhere. The transcript is a draft that you finish by listening.
A video you want captions for. The same transcript can be exported as SubRip or WebVTT. The subtitle generator route on this site covers that job in detail.
What a video transcript cannot tell you
The tool transcribes speech and never translates it. A video in Spanish gives you Spanish text. It does not describe what is on screen, read text in the picture, or tell you that someone laughed.
Speakers are not separated for you. If you need to know who said what, type each name yourself and carry it down the following lines.
The result is a draft, not a certified or verbatim record. Check it against the recording before you rely on it.
Before you open a long video
An hour of video is a long job on a phone and a manageable one on a computer. Decide first which device will do the work, because the speed depends on the device and not on this site.
Open the whole file, then transcribe the first five minutes before anything else. If the names, the language and the wording look right there, run the rest.
Keep the tab open and in front while a long file is read. The model works window by window, and the time estimate settles after the first window, so the early figure is rough.
When the transcript is done, download it or save it before you leave. The video stays where it was on your disk, untouched.
More questions about video to text here
Does the video leave my computer?
No. The file is read by your browser and the audio is transcribed on your device. You can check this yourself: open the browser's network panel while you transcribe, and no request carries your audio.
Why does an iPhone video take so long?
Phones transcribe on the processor and are several times slower than a laptop. Keep the screen on, keep the tab in front, and try the first five minutes before you run the whole file.
Can I transcribe only the start of a long video?
Yes. When a recording is longer than five minutes the tool suggests a five-minute preview first. Check the language and the wording there, then run the full length.
Is the video kept after I close the tab?
No. A file you opened is not offered for keeping, because it is already on your disk. Download the transcript, or save it to an optional account, before you close the tab.
How it works, where your data goes and a cloud comparison are on the home page and in the guide.