Privacy-first by design
Privacy Policy
Last updated: April 27, 2026
Overview
This tool is built with privacy as a core principle. We do not collect any personal data. How your audio is handled depends on the device you are using:
- On Desktop: All transcription happens entirely inside your browser using Whisper Small or Moonshine AI models. No audio, text, or personal information is ever sent to a server.
- On Mobile: Due to hardware limitations, your audio is uploaded to temporary storage, transcribed by Groq Cloud (Whisper Large V3), and then deleted. Groq does not use your data to train their models.
How Transcription Works
Desktop: Audio is decoded and processed entirely within your browser. English audio uses the Moonshine Base model (fast, lightweight); other languages use the Whisper Small model. Both run via WebGPU (with WASM fallback). The AI model is downloaded once from Hugging Face and cached in your browser — after that, transcription works fully offline.
Mobile: Audio is chunked and uploaded directly from your device into a temporary Vercel Blob object. The server sends the audio to Groq for transcription. After processing completes, the temporary upload is deleted and only the text is returned to your device.
Export & Continue with AI
You can export your transcript as plain text, timestamped text, Word (.docx), or PDF. All document generation happens entirely in your browser — no data is sent to any server for export.
The "Continue with AI" buttons copy your transcript to clipboard and open a third-party AI chat (ChatGPT, Claude, Gemini, or Grok) in a new tab. We do not send your transcript to these services — you paste it yourself. Each service's own privacy policy applies once you interact with them.
Browser Cache & Local Storage
The AI model weights (approximately 50–150 MB depending on language) are cached in your browser's native cache after the first download. You can clear this cache at any time through your browser settings.
We use minimal localStorage flags to remember whether the model was previously loaded (to skip redundant loading UI). We do not store audio, transcripts, personal data, or tracking identifiers in local storage.
Third-Party Services
- Hugging Face (Desktop): Used only to download open-source AI model files on first use. Their privacy policy applies.
- Vercel Blob (Mobile): Temporary storage for mobile audio uploads. Files are deleted after transcription completes.
- Groq Cloud (Mobile): Processes mobile transcriptions ephemerally. Groq does not retain your audio or use it for training. See the Groq Privacy Policy.
- AI Chat Services (Optional): ChatGPT, Claude, Gemini, and Grok are only opened if you click a "Continue with AI" button. We do not send data to them — you paste it yourself.
Children's Privacy
This service does not knowingly collect any data from children or anyone else, as no personal data is collected at all.
Changes to This Policy
If this policy changes, the updated version will be published at this URL with a revised "Last updated" date.
Contact
Questions? Reach out via LinkedIn.
Developed by Onat Özmen
Back to app