Why does this page use the Best model by default?

Because in our tests the smaller models were not accurate enough for Danish. Best is slower and a bigger one-time download, but the output is usable.

Does it write æ, ø and å correctly?

Yes. The output is standard written Danish with diacritics and punctuation.

Will automatic detection mix up Danish with Norwegian?

It can, since the written languages are close. This page selects Danish explicitly so detection is not involved.

Transcribe Danish Audio to Text — Free, No Upload

Convert Danish audio or video into text in your browser. 100% free, no per-minute limit, no account — nothing is uploaded. Opens with the most accurate model selected.

Model

Spoken

Output

Timestamps [0:05]

⬇️ One-time download: 269 MB (Best model 238 MB + 31 MB audio engine, shared with the video tools) — only the first time: it stays saved in your browser, so next time it starts right away. (Translating or switching model needs its own file; a browser can clear this cache if storage runs very low.) Processing takes about 25-50 min per 10 minutes of audio on a typical laptop.

What exactly is downloaded — and is it safe?

• The speech model is OpenAI's Whisper, open source, converted to run in browsers. The audio engine is FFmpeg, the open-source tool behind most video software.
• They come from Hugging Face and unpkg — public repositories used by researchers and developers worldwide, not from us.
• They are not programs. Nothing is installed, no permission is asked, and your browser keeps them in its own cache exactly like it keeps a website's images.
• They can't read your files or touch anything outside this page. Remove them any time by clearing this site's data in your browser.
• Your audio never goes the other way: this site has no server receiving files.

Drop your video or audio here or click to choose

transcribed on your device by OpenAI's Whisper — your recording is not uploaded

ℹ️ Use a recording on your device that you own or have permission to process. This tool cannot fetch YouTube or social video links. Start with a short clip. Larger models can improve accuracy but require more memory and download data. Processing time varies by device, model and recording length. Always review the result.

Danish is one of the hardest languages for speech recognition, and we would rather say so than pretend. The soft consonants, the stød and the way endings get swallowed mean that the smaller models produce Danish that looks plausible but is wrong in the details. In our test with real Danish speech the language was detected correctly, but the medium model got too many words wrong to publish as-is.

That is why this page opens with the Best model already selected: it is a larger one-time download and slower, but it is the difference between a transcript you edit and one you retype. Clear speech from a lecture, interview or meeting is the good case; fast conversation between several people is the hard one. Everything runs in your browser, free and without limits, and the recording stays on your device.

More sizes & options

Frequently asked questions

Why does this page use the Best model by default?: Because in our tests the smaller models were not accurate enough for Danish. Best is slower and a bigger one-time download, but the output is usable.
Does it write æ, ø and å correctly?: Yes. The output is standard written Danish with diacritics and punctuation.
Will automatic detection mix up Danish with Norwegian?: It can, since the written languages are close. This page selects Danish explicitly so detection is not involved.

Guides

Related tools

🔒 Private mode (the default): your recording never leaves your device. Instant mode is optional, you switch it on yourself, and it sends the audio to the browser's speech service.