Skip to content

Polish transcription

Polish audio and video to text

Upload Polish audio or video and get an editable transcript with timestamps. Polish is among the better-covered languages for Whisper-family models, so clear speech is transcribed well, with diacritics and case endings intact. The places to check are proper names, dialect speech and fast, overlapping conversation.

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

Dialects and regional speech

Standard Polish is understood across the country and among Poles in the UK, Germany, Ireland and the United States. Regional speech, such as Górale highland Polish, adds vocabulary and sounds that depart from the standard. Silesian and Kashubian speech are not Polish and will come out wrong. Older speakers, heavy rural accents and emigrants who mix in English or German words also raise the error rate, so correct more on those recordings.

Diacritics, case endings and punctuation

Polish uses ą, ć, ę, ł, ń, ó, ś, ź and ż. Words that sound alike are spelled differently, ó and u, ż and rz, ch and h, so homophone spelling is a typical slip. Seven cases change the endings of names and numbers (w Warszawie, z Marcinem), so a name may not appear in the form you search for. Quotation marks are normally „…”, and the tool follows the model's punctuation.

What speakers of Polish use it for

Students record wykłady and seminaria for revision. Journalists, historians and family researchers transcribe interviews and recordings of older relatives. Podcasters and YouTubers add Polish napisy. Teams record spotkania held over video calls to write up action points. Many people also turn voice notes into text they can search later.

Which model works best for Polish

Polish 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).

Clear single-speaker Polish suits the small model. Fast speech with long consonant clusters, ó and u or ż and rz spellings, and inflected surnames deserve a proof-read. Older speakers or regional accents benefit from a clean recording and a full read-through.

Subtitles and captions in Polish

Polish typography avoids leaving one-letter words (i, w, z, a, o, u) at the end of a line, so break before them when you edit. Aim for two lines of about 42 characters. Confirm that ą, ę, ł and ż display in your player; SRT and VTT exports are UTF-8, so YouTube and VLC show them. Subtitles stay Polish.

The uploader is set to Polish

The upload box on this page transcribes as Polish, 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

Are Polish letters like ł and ż included?
Yes, they are part of normal Polish output. The usual errors are homophone spellings, such as ó versus u and ż versus rz, so scan for those.
Can it handle Silesian or Kashubian?
No. They are different from standard Polish and will come out as guesses or errors. Gorale and other regional Polish accents are easier, but still need checking.
Can I transcribe a Polish interview with two people?
Yes. Upload the file, then label speakers and correct lines in a free account. See interview transcription for the workflow.
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.