Does it work with Flemish?

Yes. Netherlands Dutch and Belgian Dutch are both in the training data; you do not need to choose. Heavy dialect is where accuracy falls.

Can it transcribe WhatsApp voice notes?

Yes. Export the .opus file from WhatsApp and drop it here; no conversion needed.

Is this acceptable under the AVG (GDPR)?

The audio is processed in your browser and never transmitted, so there is no data transfer and no third-party processor. Your own organisation’s rules still apply to what you do with the transcript.

Transcribe Dutch Audio to Text — Free, No Upload

Turn Dutch or Flemish audio and video into text in your browser. 100% free, no per-minute limit, no signup — the file never leaves your computer.

Model

Spoken

Output

Timestamps [0:05]

⬇️ One-time download: 104 MB (Accurate model 73 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 4-8 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.

Dutch transcribes cleanly, including the compound words that trip up simpler tools: ziektekostenverzekering comes out as one word, not three guesses. Both Netherlands Dutch and Flemish are handled without a regional setting, and in our test with real Dutch speech the language was identified correctly on the first try.

Where accuracy drops is where it drops for every transcriber: strong dialect (West Flemish, Limburgish), several people talking at once, and recordings made from across the room. The page opens with Dutch selected and does everything on your device, which also keeps you on the right side of the AVG (GDPR) when the recording contains other people: nothing is transferred, so there is no processor to sign with. Free, no per-minute limit.

More sizes & options

Frequently asked questions

Does it work with Flemish?: Yes. Netherlands Dutch and Belgian Dutch are both in the training data; you do not need to choose. Heavy dialect is where accuracy falls.
Can it transcribe WhatsApp voice notes?: Yes. Export the .opus file from WhatsApp and drop it here; no conversion needed.
Is this acceptable under the AVG (GDPR)?: The audio is processed in your browser and never transmitted, so there is no data transfer and no third-party processor. Your own organisation’s rules still apply to what you do with the transcript.

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.