SnailText
EN

Transcribe files

Transcribe audio and video, on your own machine

Drop in an audio or video file, or a whole folder, and get a transcript back, plus SRT and VTT subtitles if you want them. It runs locally with Whisper, so nothing is uploaded and there is no per-minute meter.

No account · Nothing uploaded

SnailText Transcribe files screen: drop audio files or a folder, choose the language and output format, all on your machine.

Transcribe by format

SnailText transcribes all of these audio and video formats locally, on both Mac and Windows. Pick a format to see how it works, or just drop your file into the app.

Generate subtitles

Need an SRT or VTT file instead of a plain transcript? Choose the subtitle output before the run and SnailText writes a subtitle file with phrase-level timestamps, all on your machine.

File transcription FAQ

Is transcription done locally or in the cloud?
Locally. SnailText transcribes your audio and video files on your own machine with the Whisper speech model. Nothing is uploaded to a server, and there is no per-minute meter. Online transcription tools upload your file, which SnailText does not do.
What audio and video formats can SnailText transcribe?
Audio formats like MP3, WAV, M4A, AAC, OGG, Opus, and FLAC work immediately. Video formats (MP4, MOV, MKV, WebM) and a few extra audio formats use a one-time codec pack the app downloads for you. Pick any format page below for the specifics.
Can SnailText make SRT or VTT subtitles?
Yes. Choose SRT or VTT as the output before you run a transcription and SnailText writes a subtitle file with phrase-level timestamps, ready to drop onto a video. You can also export plain text, Markdown, or JSON.
How much does file transcription cost?
The free tier transcribes locally with the compact Whisper models, no account and no per-minute charge. Pro adds larger, more accurate models and an optional on-device AI cleanup pass, $7.49/mo or $89/yr for up to 3 devices.

Transcribe your files locally

Free local transcription, no account needed. Audio and video to text, plus SRT and VTT subtitles, on Mac and Windows.