Audio to text, with the speakers labeled
Upload any audio file and get back a clean, speaker-separated transcript you can relabel and export — TXT, SRT, DOCX, or JSON.
- 1
Drop in your file
Audio or video — the audio is extracted in your browser.
- 2
We transcribe & separate speakers
You get a clean, speaker-labeled dialog.
- 3
Relabel & export
Name the speakers, then download as TXT, SRT, DOCX, or JSON.
Most transcribers hand you an undifferentiated block of text. Hushscript converts your audio to text and separates each speaker, so an interview or meeting reads like the conversation it actually was.
Why Hushscript
Private by design
Your video never uploads — the audio is extracted in your browser and deleted after transcription.
Dialog, not a wall of text
Automatic speaker separation lays the result out as a conversation.
No subscription
Prepaid minutes, 10 free to start; they expire only after 6 months of inactivity.
Frequently asked questions
What audio formats can I convert?
Common formats like MP3, M4A, WAV, and more. Your browser converts the audio to a compact FLAC before upload.
Do you keep my audio?
No — the uploaded audio is deleted the moment your transcript is ready, and the speech engine retains nothing.