How to add captions to a video
- Choose your video. Drop an MP4, MOV or WebM file into the box. On a computer it can be up to 10 minutes long; on a phone, up to 90 seconds.
- Pick the spoken language and press Make captions. Your browser listens to the video and writes down every word with its timing. The first time, it downloads the free speech model once; after that it starts right away.
- Check the captions. Play the video: the captions appear on top of it, exactly as they will look in the export. Tap a caption in the list to jump to it, fix a word, or change its start and end time.
- Choose a style, a position and a size, then press Export video (MP4). When it's done, the video downloads with the captions burned in and the original sound.
You can also download the captions as an SRT or VTT file, for YouTube, a video editor or any platform that lets viewers turn captions on and off.
Caption styles
Short videos are often watched with the sound off, so captions need to be easy to read at a glance. Each style is made for that:
- Bold outline: large white letters with a black outline, readable on any background.
- Highlight word: the same, with the word being spoken shown in yellow, so viewers can follow along.
- Dark box: white text on a dark box, best over busy or bright footage.
- Minimal: lighter text with a soft shadow, for a calmer look.
Captions are kept short, one or two lines of up to about 32 characters, so they don't cover your face or the app's buttons. On tall videos, the bottom position sits above the area where Instagram and TikTok show their buttons.
Captions in Arabic
Arabic captions are written right to left, word by word, with fonts made for Arabic (Cairo and Tajawal). If you pick a font that has no Arabic letters, Spokly switches to Cairo for Arabic captions automatically. For dialects, choose your dialect in the spoken language list and use the Accurate setting on a computer.
Exporting for Instagram, TikTok and YouTube Shorts
The export is an MP4 file with H.264 video and AAC sound, the format these apps ask for. It keeps your video's resolution up to 1080p and its original sound. Exporting plays your video once in the background, so it takes about as long as the video itself; keep the tab open until it finishes. If your browser can't make MP4 files, Spokly tells you before you upload anything, and suggests what to do.
Private by design
Your video never leaves your device. The speech model and the video encoding both run in your browser, so there's no upload, no account and no watermark.