Video to text: transcribe MP4 and MOV files

Screen recordings, webinars, on-camera interviews, phone videos: if there is speech in it, you can turn it into text. Drop the video in and Skeleton Fingers transcribes what is said.

No need to pull the audio out first

A lot of guides tell you to convert a video to MP3 before transcribing it. You can skip that step. Upload the MP4 or MOV file as it is, and Skeleton Fingers transcribes the speech in its soundtrack.

Common sources that work this way:

• iPhone videos, which the Camera app saves as MOV files.
• Mac screen recordings, saved as MOV.
• Zoom, Teams and Google Meet recordings, which you download as MP4.
• Webinar and course exports, and most video editors' MP4 exports.

What you can do with the transcript

• Write a blog post, article or summary from a talk or webinar.
• Pull quotes from an on-camera interview.
• Draft captions or subtitles from the text.
• Search a long recording for the moment something was said.

Two lanes

In your browser

Free, unlimited and no account needed. The Whisper speech model runs on your own device, so the video never leaves it. This is the lane for unreleased footage, internal recordings and anything confidential. It is slower than the fast lane and the speed depends on your computer; the first run downloads the model once. It does not label speakers.

Fast

Your browser converts the video's soundtrack to audio and uploads that audio (about 115 MB per hour), not the video itself, and our servers transcribe it in seconds. The first two steps depend on your device and connection, so the total time varies. You get speaker labels and automatic language detection. It needs a free account. The converted audio and the transcript are stored with your account, and the original video file may also be saved to your account in the background; that save can fail or be skipped for large files. Whatever is stored stays until you delete that transcript or your account; nothing is deleted automatically.

How to transcribe a video

1. Open Skeleton Fingers in your browser.
2. Choose "In your browser" or "Fast".
3. Drop in the MP4 or MOV file.
4. Review the transcript and check names, figures and technical terms against the video.

What it costs

Fast minutes are counted by the running time of the video. A free account transcribes videos up to 30 minutes free, 3 a day, enough for a few short clips. Longer videos use pack hours for their full running time: an hour pack is $5 for 3 fast hours, paid once, and the hours never expire, so a one-hour webinar still leaves two hours for later. Pro is $9.99 a month for 10 fast hours if you work with video every week. The browser lane is always free.

Tips for better video transcripts

• Use a microphone, not the camera's built-in one, when you can. Camera microphones pick up the room as much as the speaker.
• Turn background music down under speech. Music under a voice is one of the most common causes of missed words.
• Trim intros and outros. Title cards and music beds cost fast minutes without adding words.