Skip to content

Finnish transcription

Finnish audio and video to text

Upload a Finnish recording and get a timestamped transcript to edit and export. Finnish is spoken quite as it is written, which helps, but its long compound words and the difference between spoken and written Finnish mean you should check the output.

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

Spoken Finnish and dialects

Everyday Finnish (puhekieli) differs a lot from book Finnish (kirjakieli): mä and sä instead of minä and sinä. A transcript can land on either, so choose one style and edit toward it. Regional speech from Savo, the east or the west, Helsinki slang, and Finnish spoken by Swedish-speaking Finns is harder than clear standard speech.

Vowel length and long words

In Finnish a doubled letter changes the word: tuli is fire, tuuli is wind and tulli is customs. A single missed length is a real error, so listen for it. Words also take many endings, so taloissanikin means 'also in my houses', and rare forms are where mistakes appear. The letters ä and ö are kept.

What Finnish speakers use it for

University lectures, meetings of clubs and housing companies, interviews, podcasts, and captions for Finnish videos. Because Finnish is spoken by few people worldwide, there are few other tools, which makes a transcript you can search and edit particularly useful, for example when you need the exact minute a decision or a quote was spoken.

Which model works best for Finnish

Finnish is supported with a good amount of training material, but less than the largest languages, so the small model makes more slips than it does for English or Spanish, especially on rare words, names and fast or noisy speech. Expect a draft that needs a proper read-through.

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). In an account, pick Small in the model menu rather than Auto: Auto prefers the fastest, least accurate model for long files or a busy queue.

Finnish endings and vowel length are the usual trouble for the small model, and rare names and compound words can be mangled. Proof-read for missed double letters, and use short clips with one speaker. A larger self-hosted model copes better with long words.

Subtitles and captions in Finnish

Finnish words are long, so a subtitle line holds fewer words than in English. Never split a word in the middle, give a line a little more screen time, and keep to two lines of roughly 40 characters. SRT and VTT exports are UTF-8, so ä and ö display correctly, and the captions are in Finnish.

The uploader is set to Finnish

The upload box on this page transcribes as Finnish, 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

Will it write spoken Finnish like mä and sä?
It can write either, depending on what is heard and how it is interpreted. Read the result and standardise the style you prefer in the editor.
Why do some words come out slightly wrong?
Finnish uses endings for most grammar, and one letter can change the case or meaning. Check each unusual word against the audio.
Can I make Finnish captions for a video?
Yes. Proof-read the transcript, then export VTT or SRT. See how to add subtitles to a video.
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.