Skip to content

Swedish transcription

Swedish audio and video to text

Upload a Swedish recording and get a timestamped transcript you can edit line by line and export as text or subtitles. Swedish is well covered by speech models, so standard rikssvenska in clear audio usually comes out readable; the work is mostly in names, compounds and strong regional speech.

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 Finland Swedish

Standard Swedish (rikssvenska) as heard on radio and television is the easiest case. Strong Skånska, Gothenburg speech, Norrland dialects and Gotland speech are harder, and so is the Swedish of Finland (finlandssvenska), which has its own intonation and some vocabulary. Fast conversation with several people talking at once is where mistakes pile up.

Å, ä, ö and compound words

The letters å, ä and ö are part of the text and display fine. Swedish joins words into long compounds, such as arbetsgrupp or hyreskontrakt, and a transcript may split one that belongs together. This is the classic särskrivning mistake, and it can change the meaning, so look for it when proof-reading. Numbers and names are the next thing to check.

What people in Sweden use it for

Lectures and seminars at universities, meeting minutes for workplaces and associations (föreningar), interviews for journalism or research, podcasts, and subtitles for videos that need to be accessible. Many Swedes also mix in English terms at work, which are worth a second look. Searching the finished transcript for a name or a number is much faster than replaying the recording.

Which model works best for Swedish

Swedish 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.

The small model handles clear, standard Swedish reasonably well, but it stumbles on proper names, rare compounds and English words dropped into a sentence. Dialect-heavy or noisy recordings benefit from a closer proof-read, or from self-hosting with a larger model.

Subtitles and captions in Swedish

Swedish subtitles usually run two lines of about 37 to 42 characters, and Swedish compounds can be long, so avoid breaking a line in the middle of one. Split at a clause boundary instead. The SRT and VTT exports are UTF-8, so å, ä and ö appear correctly everywhere. They stay in Swedish.

The uploader is set to Swedish

The upload box on this page transcribes as Swedish, 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

Does it work for Finland Swedish?
It is the same language setting, and clear speech often works. The different intonation and some local words can cause extra errors, so read through the result.
Why are some Swedish words split in two?
Swedish compounds are written as one word. If the transcript splits one, join it in the editor. Search for the pieces to catch every case.
Can I get Swedish captions for YouTube?
Yes. Export SRT or VTT after proof-reading, and upload it to the video. The captions are in the spoken language.
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.