Video to Text: Transcribe Video into Subtitles and Text

Video to text and video transcription

Converting video to text and transcribing a video are the same job: the words spoken in a video, written out with their timings. What changes is the file you take away. Subtitles keep each line timed to the picture; a text file or a document keeps the words in paragraphs to read, quote and edit.

This converter makes all of them from one transcription: transcribe video to text once, then download subtitles for the video and a document for the notes without spending credits twice.

Why only the sound uploads

A video is mostly picture. The sound track of a phone video is often a hundredth of the file, and that is all a transcription needs. Your browser takes the sound out, copying it as it is wherever it can, and sends that alone; the picture plays from your own device when you check the subtitles.

The upload is therefore quick even for a long recording on a slow connection, and the length you pay for is the length of the sound.

Choosing subtitles: standard or short

Standard subtitles suit landscape video: two lines of up to 42 characters (16 in Chinese, Japanese and Korean), at most seven seconds on screen. Short subtitles suit vertical video: one line of about three words (up to eight Chinese characters), quick to read in the middle of a phone screen.

Both come as SRT or VTT. SRT is the format most editors and players accept; VTT is the one web players read, and it marks who is speaking. Standard subtitles stay up long enough to read, short ones keep pace with the speech, and each line clears before the next one starts.

Adding the subtitles back to your video

Desktop editors, media players and video platforms all take these files.

1. 1In a desktop editor, import the SRT and drop it on the timeline above the video; the lines arrive already timed.
2. 2In a media player, give the SRT the same name as the video and keep them in the same folder, and the player loads it by itself.
3. 3On a video platform, upload the SRT or VTT as the video’s subtitle file in its settings.
4. 4For a vertical clip, choose short subtitles before converting, or switch the style after and download again.

Rename speakers in the editor, then download again: the new names go into every file at once.

Videos with several sound tracks

MKV and MP4 files can hold more than one sound track, such as an English and a Spanish version, or a voice and a director’s commentary. When the studio finds several, it lists them by language and title. Pick one and the converter transcribes that track; pick another to transcribe it too.

Phone videos, screen recordings and noisy scenes

Phone videos come as MOV from an iPhone and MP4 from most Android phones, and both convert as they are. Screen recordings saved by a browser are WEBM files; their sound often starts a moment after the picture, and the converter keeps the subtitles on the picture’s clock.

Clear speech converts best. If music or wind covers the voice, run the sound through the audio enhancer first. To note laughter and applause in the text, turn on “Mark sounds such as laughter”.

Videos from links

The converter works on video files on your device. Save the video to your device first, then drop it here. To keep only the sound as a small file, the video to MP3 converter takes it out in your browser.