Generate timestamped cues
Transcribe the recording and keep the model-generated timing for each segment.
Audio to SRT subtitle generator
Convert audio to SRT subtitles
Create SRT or VTT subtitles from MP3, WAV, M4A and other audio. EarScribe keeps Whisper timestamps, flags common readability problems, and lets you improve line breaks before export.
- Subtitle check for long, fast, repeated or overlapping cues
- Click a cue to listen before changing the text
- Export SRT, VTT, TXT or JSON from the same result
Drop an audio file or click to browse
MP3, WAV, M4A, OGG, FLAC, WebM — practical length depends on device memory
Review the transcript before you export
From audio to publishable subtitles
Run the subtitle check
Review cues that are too long, unusually fast, repeated, empty or overlapping.
Watch through and export
Improve line breaks, listen through important sections, then export SRT or VTT for your editor or video platform.
Subtitle readability basics
Two short lines are usually easier to read than one long line.
Fast dialogue may need shorter wording or more carefully split cues.
Names, numbers and on-screen terminology deserve a final manual check.
Questions about this workflow
What is the difference between SRT and VTT?
Both store timed captions. SRT is widely accepted by video editors and platforms; VTT is designed for web video and supports additional web caption features.
Does EarScribe automatically fix every subtitle?
It can improve line breaks and flag common problems, but important videos still need a final watch-through for wording and timing.
Can I edit subtitle text before downloading?
Yes. Edit the timestamped transcript, return to the subtitle check, and export the updated SRT or VTT.