PixThru

Transcribe Greek Audio to Text — Free, No Upload

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

Model
Spoken
Output
⬇️ 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.

Greek comes out in Greek script with the tonos accents in place, not in Greeklish. That is the detail that decides whether a transcript of a lecture, interview, sermon or meeting can be used as a document. In our test with real Greek speech the language was detected correctly and the accents were where they belong.

The same test showed the smaller models swapping similar-sounding words (κολυμπήσετε became κολλημήσετε), so this page opens with the Best model already selected: a larger one-time download, slower, and clearly more accurate. Standard Modern Greek from Greece and Cyprus is the good case; heavy Cypriot dialect and Pontic lose accuracy. Everything runs in your browser, free and without limits, so the recording never leaves your device.

More sizes & options

Frequently asked questions

Why is Best the default here?
Because in our tests with real Greek speech the smaller models confused similar-sounding words too often. Best is slower but produces text you can edit rather than retype.
Greek script or Greeklish?
Greek script, with tonos. If you need Greeklish you can convert the text afterwards, but the model writes proper Greek.
Does Cypriot Greek work?
Standard Greek spoken in Cyprus transcribes well; strong Cypriot dialect loses accuracy.
Is there a file-size or minute limit?
No. The limit is your device’s memory, and nothing is uploaded.

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.