Skip to main content

How transcription works in Hushscript

Here's how transcription works in Hushscript, from preview to export: the private part happens before anything is sent.

How it works

  1. 01

    Upload one file or a batch

    Common audio and video formats work, up to 10 hours long, with no file-size limit – large video and audio are staged in your browser. Queue several files or merge related recordings, and preview 30 speaker-labeled seconds before you commit. Compatible audio uploads as-is; from video, a compatible audio track is copied out in your browser – the video itself never uploads.

  2. 02

    Choose options and saved context

    Pick the source language or auto-detect, and turn on speaker detection or multichannel if the file needs them. Apply a saved dictionary or prompt preset so recognition carries over from past uploads, or add one-off keyterms or a one-off prompt for just this job. Medical mode and translation targets show additional billed minutes before you start.

  3. 03

    Transcribe in 99 languages

    Hushscript detects the spoken language automatically and transcribes it: around 99 languages, eighteen of them on our flagship model for top-tier accuracy.

  4. 04

    Edit the transcript

    The transcript arrives with speaker labels; rename them, edit segments, tag sections, or find and replace a misheard word throughout.

  5. 05

    Generate free Insights

    Choose Generate Insights to create the complete revision-bound result for free in one run: summaries, actions, decisions, open questions, quotes, chapters, speaker topics, subject clusters, export suggestions, terminology and profanity findings, and cleanup. Review cleanup in Edit; nothing changes until you approve it.

  6. 06

    Export in 21 formats

    Download as TXT, SRT, VTT, CSV, TSV, Markdown, HTML, RTF, XML, JSON, DOCX, PDF, XLSX, ODS, ODT, ASS, TTML, SBV, LRC, FCPXML, or EDL. That's 21 formats total, unwatermarked. Prebuilt archive packs bundle several at once, and a password-protected .husharchive keeps sensitive results locked until you share the password.

  7. 07

    Retention and deletion

    Audio is deleted after the transcript is saved. Set an account-default retention window and override it per transcript as needed: keep everything, or auto-delete after 7, 30, 90, or 365 days. Single-transcript, AI-artifact, and account deletion flows return downloadable receipts.

Verifying your card unlocks 30 free minutes. We place a temporary $1 hold to confirm the card is real, then release it right away, so you're never charged for the free minutes. If a card can't be verified, your 30 free minutes arrive with your first purchase instead. After that, you pay only for the minutes you use, from about a penny a minute, no subscription.

Start with 30 free minutes

Start – 30 free minutes