Upload a video file, generate subtitles from its audio track with Whisper, then review and export as SRT, VTT, or ASS.
Upload a video, run Whisper, and download timestamped subtitles as SRT, VTT, or ASS after editing them in the browser.
Turn spoken dialogue in your video into text automatically, with timestamps aligned to when each line is said.
Drop in MP4, WebM, MOV, MKV, or other common formats. No need to strip or convert the file before you start.
Let the tool auto-detect the language or choose one yourself, including English, Chinese, Japanese, Spanish, and more.
Skim the preview, double-click any line to fix mistakes, then pick SRT, VTT, or ASS and save a file for players or editors.
Drag and drop or choose a video file such as MP4, WebM, MOV, or MKV. Only video uploads are accepted on this page.
Pick auto-detect or a specific language, then generate. Whisper processes the audio and returns timed segments.
Fix mistakes in the preview, choose SRT, VTT, or ASS, then download for VLC, Premiere, YouTube, or any editor.
Use video transcription when you want to upload a clip directly and generate timed subtitles from its audio track without extracting the audio first.
Generate SRT or VTT captions for videos before uploading or republishing.
Create captions for lessons, tutorials, webinars, and training material.
Export timed subtitles for Premiere, DaVinci Resolve, Final Cut, or web players.
The audio track matters more than resolution; clear dialogue gives better captions.
Compress or trim very large videos before upload for faster processing.
Check speaker names, brand terms, and timestamps before publishing.
Use SRT for general upload, VTT for web playback, and ASS for styled desktop playback.