Bringing the video in
Drop in the video file unchanged: MP4, MOV, MKV, WEBM, AVI, M4V, 3GP or a phone screen recording. The sound track is pulled out on the server, so there is no convert-to-MP3 step, and every timestamp still matches the picture. If the video is online, paste its public link under Import from link: YouTube, Shorts, TikTok, public Vimeo, Dropbox or Google Drive share links, or a direct link to a video file. Only the audio is downloaded. Playlists and channels are refused, so queue videos one link at a time, and sign-in-only posts such as Instagram need to be downloaded and uploaded.
After processing, the draft follows the video. Click any line to hear it, type over the mistakes, and the change is saved.
Cyrillic output and a rough draft
The draft is written in Mongolian Cyrillic, the alphabet used in Mongolia, including ө and ү. The traditional vertical Mongolian script, used in Inner Mongolia in China and in some formal writing in Mongolia, is not produced.
Mongolian has limited training data, so treat the output as a rough draft: long suffixed words, vowel harmony and names are frequent errors, and some lines will need rewriting. It works best on slow, clear speech from one person. Russian and English loanwords are common in technical and business talk, and Mongolians studying or working in South Korea often mix in Korean words.
Mongolian videos people transcribe
Examples:
- News clips and interviews from Mongolian TV and YouTube.
- University lectures and online lessons.
- Buddhist teachings and ceremonies.
- Family videos and Naadam or Tsagaan Sar gatherings.
- Your own videos, for Mongolian subtitles.
Subtitles and documents
Export SRT or VTT after correcting; ө and ү display correctly from the UTF-8 file in YouTube and most video editors, provided the font covers extended Cyrillic. DOCX, PDF and TXT keep a written copy, and CSV lists each line with its start time.
Tips and translation
Use a close microphone and turn on audio repair for wind or crowd noise; throat singing and long songs are not a good fit, since the model is trained on speech. Speaker labels are available on paid plans and with a Minute Pack.
The transcript stays in Mongolian. For an English reading, open the Google Translate link on the transcript, or use the AI prompt export to hand the text to ChatGPT, Claude or Gemini. For audio-only recordings, see the Mongolian audio to text page.