Transcription
Transcribe audio and video to text — offline
SweetWhisper turns audio and video into text right on your Windows PC: pick the files, get the text. No internet, no uploads, no length limit.
File transcription is part of Pro: free for the first 14 days after you install, then a one-time purchase — no subscription. What Pro includes
How to transcribe a recording
Install SweetWhisper
The speech model downloads inside the app. No Python, no command line.
Choose “Transcribe from files”
It sits in the tray icon’s menu and in the floating bar’s menu. Pick one file or several.
Wait for the text
You can see which file is in progress and cancel at any time. If a video has several audio tracks, the app asks which one to use.
Get the result
Copy the text or paste it straight into another app. A .txt file also appears next to the original.
What it handles
- Audio
- wav, mp3, m4a, aac, ogg, oga, opus, flac, wma, webm
- Video
- mp4, mkv, mov, avi, flv, webm — the app pulls out the sound itself, nothing else to install
- Length
- Any: a full lecture or an hour-long meeting goes through in one pass
- Output
- Text plus a .txt next to the recording; from History, SRT and VTT subtitles and text with timestamps
- Speakers
- Text split by voice — “Speaker 1: …”. Up to 8 speakers, or let the app decide
- Translation
- Translate the finished text into English or 14 other languages
Frequently asked questions
Does transcription need the internet?
No. You need it once, to download a speech model. After that everything runs offline and the recording never leaves your computer.
Can it tell speakers apart?
Yes. It needs one extra model, downloaded once. Set the number of speakers (up to 8) or let the app work it out. Works with the Whisper and Parakeet models.
How much does it cost?
File transcription, subtitles, speaker labels and translation are part of Pro. They are free for 14 days after you install, then a one-time purchase with no subscription. Voice typing into any app is always free.
Can I transcribe a file on my phone?
No, file transcription is Windows-only. The Android app is offline voice typing in any app.