Hushscript
Private transcription without the local AI setup.
I founded Hushscript and designed and built it: private, browser-based audio and video transcription that turns a recording into an editable, speaker-labeled transcript. Compatible video stays on your device, and there is no subscription, only prepaid minutes. The product site is hushscript.com.
What is Hushscript?
Hushscript turns an audio or video recording into a clean, speaker-labeled transcript you can edit, translate, analyze, and export. It works in the browser, with no local AI models to install.
I built it for people whose recordings are sensitive or valuable — journalists, lawyers, researchers, therapists, founders. Compatible video never leaves your device, the audio sent for transcription is deleted after processing, and there is no subscription: you pay only for the minutes you use.
What does it do?
Speaker-labeled transcripts
Automatic speaker detection, included at no extra cost. Rename speakers and edit inline.
~99 languages
Transcribe in about 99 languages, detected automatically, with EU data residency available.
Free AI insights
One optional pass adds summaries, action items, decisions, chapters, and key quotes.
21 export formats
TXT, SRT, VTT, DOCX, PDF, JSON and more — plus password-protected archives. No watermark.
Privacy by design
Compatible video stays on your device, transcription audio is deleted after processing, and stored data is encrypted.
No subscription
Prepaid minutes instead of a monthly plan. Start with 30 free minutes.
What can developers build on it?
Chrome extension
I built an extension that records a tab, the microphone, or both. The recording is saved locally, and it is transcribed only when you upload it.
SDKs
Official SDKs for TypeScript, Python, Go and PHP turn a recorded file into a transcript with one call.
CLI
The command-line tool, built on the TypeScript SDK, reached 1.0 in October 2026 and runs the same transcription from a terminal.
MCP server and API
The remote MCP server has OAuth sign-in and 50+ tools that let AI agents upload, transcribe, edit and export inside an account. The REST API comes with an OpenAPI document.
Frequently asked questions
Is my audio private?
I designed Hushscript around privacy. Compatible video is prepared in your browser, so the video stays on your device and only the audio needed for transcription is sent. That audio is deleted after processing, and the data Hushscript stores for you is encrypted.
Which export formats are there?
I built Hushscript with 21 export formats, including TXT, SRT, VTT, DOCX, PDF and JSON, plus password-protected archives. Exports carry no watermark. Before you export, you can rename speakers and edit the transcript inline, and an optional AI pass adds summaries, action items and key quotes.
How do I pay for Hushscript?
There is no subscription. I built Hushscript around prepaid minutes, so you pay only for the minutes you use instead of a monthly plan, and you can start with 30 free minutes. Speaker detection and the optional AI insights pass are included at no extra cost.
Where can I find Hushscript?
Explore Hushscript
Follow Hushscript