Skip to content

Russian transcription

Russian audio and video to text

Upload Russian audio or video and get an editable, timestamped transcript in Cyrillic. Russian is one of the languages Whisper-family models have a large amount of training audio for, so clear speech comes out well. Names, brand names in Latin letters and mixed Russian-Ukrainian speech are the first places to look.

Free preview: one file up to 15 minutes and 25 MB, 3 tries a day, no account needed.

Want to keep your transcripts? Create a free account

Accents, regions and mixed speech

Standard Moscow-style Russian is the easiest case. Russian spoken in Ukraine, Belarus, the Caucasus, Central Asia, Israel and the diaspora is generally recognised, with more errors for strong regional accents and second-language speakers. Surzhyk, or a speaker who moves between Russian and Ukrainian, Kazakh, Georgian or English, tends to go wrong at the switch. Set the language to the one that dominates and check the switches line by line.

Cyrillic, ё and punctuation

Output is Cyrillic. Everyday Russian text often writes е where the sound is ё, so do not expect ё to appear consistently, and stress marks are not shown, which matters to learners. Quotation marks are normally guillemets («…») and dialogue uses a dash; tidy punctuation in the editor if you have a house style. Brand names such as YouTube or iPhone may be written in Latin or Cyrillic, so search for both spellings.

What speakers of Russian use it for

Students and lecturers record лекции for notes and revision. Journalists and researchers transcribe interviews. Teams record meetings and webinars in Russian. Creators caption videos and short clips. People turn long voice messages into text they can skim. Learners of Russian use a transcript to read along with native-speed speech and look up words they missed.

Which model works best for Russian

Russian is one of the languages Whisper-family models have seen the most speech in, so the small model can give a reasonable first draft from clear audio. That is not a promise of accuracy: it still slips on names, numbers, jargon and overlapping or noisy speech, so proof-read anything you will publish or rely on.

On tryscriptorium.com the no-account preview and regular accounts run the small model (the larger medium and large-v3 models run when you self-host Scriptorium).

Russian is well covered, so the small model is a reasonable fit for clear audio. Look hardest at surnames, place names and transliterated foreign words, and at passages where the speaker switches into Ukrainian or English. Noisy phone audio is the other common weak spot.

Subtitles and captions in Russian

Russian words are long, so keep lines to about 42 characters and two lines, and avoid ending a line on a one-letter word such as в, с or к. Cyrillic exports as UTF-8 SRT and VTT and displays correctly in VLC and YouTube. Decide whether you want ё before delivery, because the transcript will not add it consistently. Subtitles stay Russian.

The uploader is set to Russian

The upload box on this page transcribes as Russian, so the recogniser does not have to guess the language from the first seconds. If the recording is in another language or switches languages, use Audio to text, which detects the language automatically. Automatic transcription is a draft and no accuracy figure is promised: check names, numbers and anything you will rely on.

How it works

  1. Add a recording

    Drop in a video or audio file, choose one from your device, or record from the microphone. Nothing to install.

  2. It transcribes

    Speech becomes timestamped text, with speaker labels when more than one person talks.

  3. Read, fix, export

    Click any line to correct it, then download TXT, subtitles, Markdown, JSON or CSV.

Questions

Can it tell Russian from Ukrainian?
This page sets the language to Russian, so the model expects Russian. If the recording is Ukrainian, use the Ukrainian page instead. For a mix, choose the language that dominates and proof-read the rest.
Will it write ё?
Not consistently. Most Russian text uses е for both sounds and the model follows that habit, so run a search and replace if your publication needs ё.
Can I transcribe Russian voice messages from a messenger?
Save the voice message to your phone as an audio file and upload it. If the format is not accepted, convert it to MP3 first. Short, clear messages work best.
Which file types can I upload?
Video: MP4, MOV, MKV, WebM, AVI, M4V, WMV, FLV, MPEG, 3GP, TS. Audio: MP3, WAV, M4A, AAC, FLAC, OGG, Opus, WMA, AIFF, AMR, CAF. Anything else the server can decode as audio or video generally works too; there is no need to convert first.
Is it free?
Yes — one file up to 15 minutes and 25 MB with no account, up to 3 tries a day. A free account keeps your transcripts in a library and lifts the guest limits; the current limits and paid plans are on the pricing page.

Want your transcripts saved and longer files? Create a free account · See pricing · All use cases

Try it with your file

No account needed for a first transcript.