Vocap

Vocap listens to the speech in a video on the device itself, times every word, and burns the captions into a copy you can post. There is no upload and no queue: the recognition and the rendering both happen on your iPhone.

What it does

• Recognises speech on-device and times each word individually.
• Sixteen caption looks — plates, outlines, glows, karaoke fills, word-by-word arrivals.
• Reframes to 9:16, 4:5 or 1:1 and saves back to your photo library.
• Exports a SubRip .srt file, free, with no watermark on anything.