HushscriptAudio and video transcription that stays private

Your source video stays on your device: Hushscript prepares the audio in your browser and sends only that for transcription. Hushscript removes its transcription audio after processing and never trains on your recordings. Stored transcripts are encrypted at rest, and you choose how long they stay. Private mode saves no transcript to your account; speech recognition still runs online, and you get a password-protected archive.

Transcription turns spoken audio or video into written text, called a transcript. To transcribe a video or get a transcript from video, add a local file. For audio, you can also use a supported audio link or a short in-browser recording. Either way, preview up to 5 minutes first. After you sign in, choose the full transcription settings and Hushscript creates an editable, timecoded transcript. Local video is prepared in your browser, so the source video stays on your device.

Yes, three ways. Use Hushscript as a free transcriber for a preview of up to 5 minutes before you create an account; a new personal account gets a free preview of up to 5 minutes from its first upload in the app; and eligible personal accounts get 30 free minutes once, after card verification or with a first purchase. Full transcription needs an account and available minutes, and longer work uses prepaid packs with no subscription.

Hushscript is an automated transcription service for interviews, meetings, podcasts, lectures, voice memos, and recorded phone calls, from audio or local video up to 10 hours. You can also merge related recordings before starting.

Yes. Correct the text and speaker names in Hushscript, then export 21 formats including TXT, DOCX, PDF, SRT, VTT, CSV, and JSON. Your first optional Insights generation is free; one free Insights run creates summaries, actions, decisions, open questions, chapters, quotes, and a complete Cleaned transcript. Later regeneration uses minutes. A password-protected .husharchive is available as a separate bundle.

Yes, when you select speaker detection, which adds no minutes. You can rename speakers or reassign individual transcript turns in the editor. It works across the supported transcription languages. Check automatic labels against the recording, since overlapping speech can fool them.

Hushscript transcribes around 99 spoken languages. The preview uses automatic detection; after you sign in, you can keep automatic detection or set the source language before the full transcription.