Why is Best the default here?

Because in our tests with real Romanian speech the smaller models made too many mistakes. Best is slower and a bigger one-time download, but the output is usable.

Does it write the diacritics?

Yes: ș, ț, ă, â and î appear as in correct written Romanian, with punctuation.

Does Moldovan Romanian work?

Yes. Accuracy is close to Romania-Romanian on clear audio, with more slips on regional words.

Can I translate to English at the same time?

Yes. Set the output language to English and the translation is produced in the same run, on your device.

Transcribe Romanian Audio to Text — Free, No Upload

Turn Romanian audio or video into text with ș, ț, ă, â and î in place, in your browser. 100% free, no per-minute limit, no signup — nothing is uploaded. Opens with the most accurate model.

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.

Romanian transcribes into proper text with its diacritics, ș, ț, ă, â and î, which matters because so much Romanian on the internet is typed without them. In our test with real Romanian speech the language was detected correctly on the first pass.

The same test showed something we would rather tell you than hide: the smaller models turn Romanian into plausible-looking nonsense, one word right and the next one invented. So this page opens with the Best model already selected: a larger one-time download and slower, but it produces Romanian you can edit rather than retype. News, lectures, interviews and calls are the good case; Moldovan Romanian works with a little more error on regional words. Everything runs in your browser, free, with no minute limit, and the recording is never uploaded.

More sizes & options

Frequently asked questions

Why is Best the default here?: Because in our tests with real Romanian speech the smaller models made too many mistakes. Best is slower and a bigger one-time download, but the output is usable.
Does it write the diacritics?: Yes: ș, ț, ă, â and î appear as in correct written Romanian, with punctuation.
Does Moldovan Romanian work?: Yes. Accuracy is close to Romania-Romanian on clear audio, with more slips on regional words.
Can I translate to English at the same time?: Yes. Set the output language to English and the translation is produced in the same run, on your device.

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.