Transcribe

Transcribe turns the audio in a layer into text you can actually work with. Point it at a voiceover, an interview, or a video clip, and it gives you the full transcript with timing for every word. It is the starting point whenever you need to caption, subtitle, or sync motion to what is being said, because once you have timed words, you can place markers, build subtitle layers, or cut to the beat of speech. If what you want is finished caption layers on the timeline, use Subtitles directly — it runs the same transcription at the same 5 credits per minute, so there is no need to pay twice.

How to use it

What you get

When the transcription finishes, two things happen:

• In the panel — the full transcript appears in a transcript section, along with a quick summary: word count, detected language, and audio duration.
• On the timeline — Prism creates a new guide layer named [Transcript] <your layer name> directly above the source layer, and places one timeline marker per sentence. Each marker holds that sentence's text and spans its spoken duration, timed to the source layer so everything lines up frame-accurately.

A few specifics worth knowing:

• Your source layer is never changed. All output goes onto a separate guide null layer, so the audio or video stays exactly as it was.
• Sentences are split automatically. A new sentence begins at sentence-ending punctuation or after a noticeable pause in speech, which is what gives you readable, well-grouped marker text.
• Re-running refreshes cleanly. If a [Transcript] guide already exists for that layer, its markers are cleared and rebuilt — you will not get duplicates stacking up.
• Word-level timing is the foundation. The raw transcript carries a start and end time for every word, so it is the source material for building subtitle layers later (the markers are the human-readable preview; the per-word timing drives precise captions).
• Wide format support. It accepts the common audio and video formats After Effects handles — for example MP3, WAV, M4A, FLAC, OGG, MP4, MOV, and WEBM. Large video files are supported, up to roughly 900 MB per upload.
• Markers outside the layer's visible range are skipped. Anything that would land before the layer starts or after the composition ends is left off; the panel reports how many markers were placed and how many were skipped.

Notes and limits

Transcribe costs 5 credits per minute of audio. For how credits are metered, the full per-tool cost table, and plan caps, see usage and limits.

Related

• Subtitles — turn the same transcription into a timed caption layer on the timeline
• Usage and limits — how credits are metered and the full per-tool cost table
• Plans and pricing — Free includes 200 AI credits a month; Pro adds more
• The Tools panel — all nine tools and what each costs
• Troubleshooting — text and format gotchas in After Effects