Tajik transcription: an honest view
Tajik is a low-resource language for the speech model. Expect a rough draft with many corrections, especially in names, numbers and fast speech. Slow, clear speech from one person gives the best draft; calls from a busy street or a family gathering will need much more fixing.
The draft is a starting point. Clicking a line replays it, so you can check a word and correct it on the spot.
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.
Tajik Cyrillic
The transcript uses the Tajik Cyrillic alphabet with its extra letters ғ, ӣ, қ, ӯ, ҳ and ҷ. These are what the draft most often gets wrong, sometimes writing the nearest Russian letter instead (г for ғ, к for қ, х for ҳ). Check them on every line you plan to use.
If you need Persian script, that is a different setting: Tajik is a variety of Persian, and the Persian option writes Perso-Arabic script. For a Tajik speaker, Tajik usually gives the closer result, and script conversion has to be done separately.
Russian and Uzbek in Tajik recordings
Tajik speech often carries Russian words, from technical terms to whole phrases, and speakers in the north and in Uzbekistan's Samarkand and Bukhara may mix in Uzbek. Keep Tajik selected when Tajik dominates. Auto-detect may pick Persian or Russian for a Tajik clip, which gives the wrong script or language, so this page sets Tajik for you.
What people record in Tajik
Uploads include voice messages and calls between migrant workers in Russia and their families, interviews for research and journalism, lectures, poetry readings and music, and radio segments. Students use it for interviews they need to quote in a thesis.
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 TikTok clip, see the Tajik video to text page.