You have a script and an audio file but no captions. Paste the transcript, say how long the audio runs, and get a timed caption file back, split at sentence boundaries with time shared out by length rather than evenly.
Free · No account · Your files never upload
Files are read in your browser. Nothing is uploaded.
Turns a plain transcript into a timed caption file. It splits the text at sentence boundaries, breaks anything still too long for your line budget, and shares the available time out in proportion to how long each chunk is.
A twelve-word sentence genuinely takes longer to say than a three-word one, so dividing the duration evenly produces captions that drift further out of sync with every cue. Weighting by character count keeps the drift small enough to correct by hand.
The tool cannot hear the audio. It does not know where the speaker paused, took a breath, or left three seconds of silence for an animation. Expect to nudge the timings against the real recording before you ship. What this saves you is the tedious part, which is typing out every timestamp from nothing.