Every word, on time.
Captions are timed word by word from your audio. Transcription supports English, Spanish, Italian, French, German, Portuguese, Russian, Japanese and Chinese.
Fix a word or nudge its timing in the editor; the style follows.
Word-timed captions in 30 styles, generated from your audio and fully editable. Pick a look, highlight the key words, and change any word or timing in the editor.
Generated in the same pass as the rest of your edit.
Press a style to play it, straight from the editor. Change fonts, colours and size to make one your own, or see all 30 styles.
Heavy outlined capitals that build word by word, with yellow and green key words.
Big, bouncy outlined comic words with green and yellow pops.
Bold all-caps short-form captions: white one-word hits with cyan support words and a heavy glow.
Heavy outlined all-caps karaoke with the spoken word in bright yellow.
Outlined white capitals with a neon-green trace on the word being spoken.
Bold white phrases with selective vivid-red key words.
Small white setup lines around a big glowing orange word.
Clean, restrained sentence-case subtitles with a soft shadow.
Your raw clips. Ready for the spotlight. Get polished edits with captions, B-roll and motion graphics - without spending hours on a timeline.
The current transcription language picker includes English, Spanish, Italian, French, German, Portuguese, Russian, Japanese and Chinese. You can edit the resulting caption text and styling in the editor.
Your next viral video is sitting in your camera roll. Let's get it out.
150 free AI credits · No credit card · Exports on paid plans