Getting the video in
Drop in the video file without converting it: MP4, MOV, MKV, WEBM, AVI, 3GP or a screen recording from your phone. The sound is pulled out on our server, and every timestamp points to the same moment in the original video. If the video is online, use Import from link: public YouTube, TikTok and Vimeo videos, Dropbox and Google Drive share links and direct file links all work. Only the audio is fetched, one video per link, and several links can wait in the queue.
The draft opens next to a player, line by line, so you can listen to each sentence and rewrite it where needed.
An honest note on Bashkir accuracy
Bashkir is one of the least represented languages in the model's training data. Expect a rough draft with many corrections; on fast, noisy or music-heavy video, a lot of lines will need rewriting. It does best with slow, clear speech from one person, such as a teacher or a speaker reading a text. Correcting a timed draft is still faster than typing from zero, and the timestamps are useful on their own for subtitles.
Bashkir Cyrillic has letters Russian lacks: ә, ө, ү, ғ, ҡ, ң, ҙ, ҫ and һ. The model may write the nearest Russian letter instead, for example к for ҡ or з for ҙ, and close Tatar spellings can appear too. Russian words and whole Russian sentences are common in videos from Ufa; those are usually written in Russian.
What gets filmed in Bashkir
Typical uploads:
- Regional TV news and interviews from Bashkortostan.
- Language lessons and school materials for Bashkir learners.
- Folklore evenings, kurai performances with spoken introductions, and festivals.
- Recordings of grandparents and village elders for family or local archives.
- YouTube and TikTok videos from creators writing captions in Bashkir.
Bashkir subtitles
Export SRT or VTT for Bashkir subtitles. The files are UTF-8 and YouTube shows the extra letters correctly; if a desktop editor shows boxes in place of ҡ or ҙ, switch to a font with full Cyrillic coverage, such as Noto Sans. DOCX and PDF keep the letters for printing.
Speaker labels are available on paid plans and with a Minute Pack.
English and audio-only recordings
The transcript is written in Bashkir as it was spoken; nothing is translated. To read it in English, open the Google Translate link on the transcript, or use the AI prompt export to hand the text to ChatGPT, Claude or Gemini. For recordings without video, see the Bashkir audio to text page.