Auto Captions
Automatic captions. Your words, on screen.
Turn spoken audio into editable captions for your shorts, tutorials and talking-head videos. ShortsJet uses local Whisper speech recognition, so your recording stays on your computer during transcription.
Try it in ShortsJet
- Local speech recognition
- Editable text & timing
- Group styling
Start with the speech in your edit
Choose a video or audio clip, or generate captions from the audible timeline mix. ShortsJet takes the selected section, playback speed and timeline position into account when placing the caption clips. Select the spoken language yourself or use automatic language detection.
This suits a direct-to-camera explanation, a recorded voiceover or a tutorial assembled from several takes. The generated text gives you a starting point that you can review alongside the picture.
Correct each line, then style the group
Names, product terms and speech in noisy recordings can need a correction. Each generated caption is an editable text clip, so you can change its words and adjust when it appears and disappears. Review the result before exporting, especially when several people speak or music overlaps the voice.
Font, size, colour, background, shadow and position can be adjusted across the generated caption group. That gives your subtitles a consistent appearance while leaving individual lines and their timing editable.
Keep transcription on your own computer
The speech tools and model are included with the distributed app. Caption generation runs locally rather than uploading audio to a transcription service. Once the app and its speech components are installed, the recognition work does not require an online speech API.
Captions normally follow the language of the recording. The optional Translate to English setting produces English text from speech in another supported language. Captions are rendered into the finished video, ready for viewers who watch without sound.
A CLOSER LOOK
Good to know.
Is my audio sent to a server to create captions?
No. Whisper speech recognition runs on your computer. Product activation is a separate process and does not need your video or audio files.
Can I edit the subtitles after they have been generated?
Yes. Correct individual text clips and their timing, then adjust the shared styling of the generated caption group.
Try it with your next video.
ShortsJet for Windows, Ubuntu Linux and macOS. Free for 30 days.
Buy a ShortsJet license