Sync Video & Audio

Frequently asked questions

What can the tool do?

You film with a camera or phone and record the sound separately, say with a clip-on microphone. The tool finds the matching spot in the audio recording for every clip, puts the good sound under the picture and writes down every spoken word with its time — including “um”, stutters and slips. One click on “Clean up” cuts filler words, repeats and long pauses; you remove single words or sentences by selecting them in the text. You get one MP4 of all clips or one file per clip.

What happens to my data?

Videos and audio recordings stay on your device: matching, cutting and encoding run in the browser. Only for transcribing and cleaning up, pieces of the audio or the text go with your own key directly to OpenRouter, which passes them on to the speech model; our server sees none of it. Your key, the transcript and your cuts stay in this browser’s storage and can be deleted there with one click.

What does it cost?

The tool is free. Transcribing needs your own OpenRouter key; OpenRouter charges your credit — about 0.4 cents per minute of audio, so roughly 11 cents for 30 minutes. The button shows the amount beforehand. Work that is already transcribed costs nothing the next time: just choose the same files.

Which files can I use?

Videos as MP4, MOV or WebM, audio as WAV, MP3 or M4A — several clips and several recordings, up to 30 minutes in total. A clip may sit in the middle of a long recording. If a clip does not match clearly, the tool says so and keeps its camera sound.

Does the quality get worse?

Not without cuts: the picture is taken over unchanged, only the sound is new. As soon as words are cut out, the browser re-renders the video at its original size and frame rate in high quality. Your original files stay untouched.