Interviews and research
Journalists and researchers turn recorded interviews in Uzbek into text; timestamps make it quick to find a quote and check it against the audio.
Upload a recording in Uzbek and get a transcript with timestamps and speaker labels. It handles interviews, lectures, meetings and videos - or paste a YouTube, TikTok or Instagram link. The first 5 minutes every day are free.
Drop an audio or video file (MP3, WAV, M4A, MP4, OGG, WEBM, FLAC, AAC) or paste a link to the video.
Pick "Uzbek" in the language list. If you do not know the language of the recording, you can leave auto-detection on.
Copy the transcript or download it as TXT, Word or PDF; with timestamps you can also export SRT and ASS subtitles.
Journalists and researchers turn recorded interviews in Uzbek into text; timestamps make it quick to find a quote and check it against the audio.
Recordings of lectures, webinars and online lessons become searchable text, so you find a phrase instead of scrubbing through the audio.
A transcript of a meeting with speaker labels shows who said what, and the minutes take minutes instead of an evening.
Recognized speech with timestamps exports to SRT or ASS - ready Uzbek subtitles for YouTube and editing.
Supported formats: MP3, WAV, M4A, MP4, OGG, WEBM, FLAC, AAC. Audio and video transcription, with export to TXT, Word (DOCX), PDF and SRT/ASS subtitles.
Uzbek (uz-UZ) is available for recognition. Kazakh, Russian, Kyrgyz and 30+ other languages are available too.
Sign up, upload the recording, choose "Uzbek" and click Transcribe. Copy the result or download it as TXT, Word, PDF or SRT.
Yes. Upload an MP4 or WEBM, or paste a YouTube, TikTok or Instagram link - the audio track is extracted automatically. If a YouTube video has captions, the text is taken from them and no transcription minutes are used.
The free plan gives 5 minutes of transcription a day (1 file a day, up to 10 MB). The Starter plan is $6.99 a month: 90 minutes a month, files up to 200 MB. See the pricing page for details.
Yes. With speaker separation on, lines are labelled per speaker - handy for interviews, podcasts and meetings.
There is an auto-detect mode, but if you know the language of the recording, select it yourself - the result is usually more accurate.
Free, no install - right in your browser.