Does it separate who is speaking?

Not yet — the transcript is continuous text. For two-person interviews the turns are usually easy to follow, and speaker labels are on our list.

Is this suitable for confidential or regulated material?

The audio is processed entirely on your device and never transmitted, which is the technical requirement most confidentiality rules care about. Check your own institution’s policy for the final word.

What if two people talk over each other?

Overlapping speech is the hardest case for any transcription, ours included. Use the Best model and expect to fix those passages by hand.

Transcribe an Interview to Text — Free & Confidential

Convert a recorded interview into text without uploading it. 100% free, no per-minute limit, no account — ideal for journalists and researchers.

Model

Spoken

Output

Timestamps [0:05]

🌍 The spoken language is detected automatically and the transcript comes out in that same language. Set it manually above if your audio is hard to hear, and use Output to translate into English.

⬇️ 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.

Interviews are the clearest case for keeping transcription on your own machine. A journalist's recording can identify a source; a researcher's audio is covered by ethics approval that often forbids third-party processing; an HR interview contains personal data protected by law. Uploading that to a free web service is, in several professions, a genuine breach — and it is what almost every transcription tool requires.

Here the audio is processed by a speech model running inside your browser, so the recording never leaves the device and no copy exists anywhere else. It is free, with no per-minute limit, which also removes the awkward habit of trimming interviews down to fit a free tier. You get plain text for quoting, or timestamped files for going back to the exact moment a sentence was said.

More sizes & options

Frequently asked questions

Does it separate who is speaking?: Not yet — the transcript is continuous text. For two-person interviews the turns are usually easy to follow, and speaker labels are on our list.
Is this suitable for confidential or regulated material?: The audio is processed entirely on your device and never transmitted, which is the technical requirement most confidentiality rules care about. Check your own institution’s policy for the final word.
What if two people talk over each other?: Overlapping speech is the hardest case for any transcription, ours included. Use the Best model and expect to fix those passages by hand.

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.