Mongolian transcription: an honest view
Mongolian is a low-resource language for the speech model. Expect a rough draft with many corrections, especially in word endings, names and numbers. It works best on slow, clear speech from one person with little background noise. Even so, correcting a draft line by line against the audio is usually quicker than typing a long interview from nothing.
Upload the recording as it is: MP3, M4A, WAV, OGG, OPUS, FLAC or AAC, a voice note saved from WhatsApp or Telegram, or a video file such as MP4 or MOV. You can also record from your microphone in the browser. Long files are split and processed in parallel, so a ten-minute recording usually takes a minute or two.
Cyrillic and the traditional script
In Mongolia, Mongolian is written in Cyrillic with two extra letters, Өө and Үү, and that is what the transcript uses. Check these letters and long vowels (аа, оо, өө) closely, because the draft often gets vowel length or harmony wrong.
The traditional vertical Mongolian script, used in Inner Mongolia and taught in Mongolia, is not produced. If you need it, you will have to convert the corrected Cyrillic text yourself.
Dialects and borrowed words
The model is closest to Khalkha, the standard spoken in Ulaanbaatar. Speakers from Inner Mongolia, Buryat speakers and western dialects will need more corrections.
Mongolian conversation often carries Russian and English words, especially in business, technology and education. They may come out in Cyrillic or Latin letters. If a recording is mostly Russian or English, select that language instead.
What people record in Mongolian
Uploads include research and journalism interviews, university lectures, podcasts, and calls with family. Mongolians studying or working in South Korea, Japan, the US and Europe use it to turn voice messages and interviews into text they can search and quote. Teachers and translators also use a corrected draft as the base for subtitles or a written summary.
Exports and next steps
Export TXT or DOCX for notes and documents, PDF for a fixed copy, SRT or VTT for subtitles, and CSV with one row per line and its start time. Timestamps and speaker names can be switched on or off in each export. Speaker labels are available on paid plans or with a Minute Pack.
For video files, such as a YouTube interview or a recorded lecture, see the Mongolian video to text page.