# Transcribing an interview offline, without sending the audio to the cloud > Transcribe an interview without uploading the audio: consent, recording, an on-device Whisper model, proofreading and anonymization. Canonical: https://ntilia.com/en/guides/transcribe-interviews-offline Updated: 2026-09-27 ## The essentials To transcribe without exposing a source, run the speech-recognition model on your own device: Whisper, an open-source model, makes that possible. Download it before you leave, record cleanly with the person’s consent, then proofread the transcript, especially proper names. ## Why transcribe on the device Most transcription services upload the audio to their servers. For an ordinary meeting that is acceptable; for a source taking a risk by talking to you, their voice and words end up with a third party. Local transcription removes that transfer, and works without a network. ## Step by step 1. **Get consent** — Say you are recording, what the recording is for, and offer anonymity when needed. 2. **Record carefully** — A quiet place, the phone close to the person, not on a vibrating table. Good audio beats a big model. 3. **Download the model before you leave** — The model downloads once, on Wi-Fi; after that it runs without a network. 4. **Transcribe and proofread** — Models mostly get proper names, numbers and mixed languages wrong. Listen again to the passages you will quote. 5. **Anonymize before sharing** — Replace names and identifying details in the text before it leaves your device. ## Which model to choose - Tiny (about 45 MB): the fastest, recommended on phones. - Base (about 90 MB): a good balance, recommended on computers. - Small (about 250 MB): more accurate, slower, for a recent computer. ## With nTilia From Pro, nTilia transcribes a note’s audio with Whisper on the device: the audio is not uploaded. The transcript lands in the note with [mm:ss] timestamps; the Outline tab lets you jump to them. On phones, you need a WebGPU-capable browser. > **Good to know** — If you later sync the note, its text is private but not end-to-end encrypted: that is what lets you publish it in the journal later. For an interview that must never leave the phone, keep it as a device-only note. ## Frequently asked questions ### Can I transcribe an interview without an internet connection? Yes, with a model like Whisper that runs on the device. You just need to have downloaded it beforehand, while you had a network. ### Is local transcription as accurate as the cloud? Small models, suited to phones, make more mistakes than the large server models. Good audio and proofreading make up for most of it. ### Is Whisper free? Whisper is an open-source model released by OpenAI. In nTilia, local transcription is included in the Pro plan. ## Go further - [Comparison: nTilia or Otter.ai](https://ntilia.com/en/compare/otter) - [Comparison: nTilia or Whisper Notes](https://ntilia.com/en/compare/whisper-notes) - [Otter.ai alternatives without the cloud](https://ntilia.com/en/alternatives/otter) - [Guide: interview transcription, method and GDPR](https://ntilia.com/en/guides/interview-transcription) - [nTilia for researchers](https://ntilia.com/en/for/researchers) - [Guide: take notes without a network](https://ntilia.com/en/guides/take-notes-without-a-network) ## Sources - [OpenAI — Whisper (GitHub)](https://github.com/openai/whisper)