How to read on-screen text at a given second

Use the single level, or inspect_frame from an agent, to get one frame at 1560 px on its long edge. A contact-sheet tile is a thirtieth of a sheet and small text on it is genuinely unreadable — this is the call that exists for that, and it costs one flat credit.

Last updated 6 August 2026

The call

Copy this as it stands. “What does the caption at 0:37 say, and how is it set?” is the question it answers.

Ask an agenttext

Read the text on screen at 0:37 in this video and describe how it is set.

TypeScript SDKts

const frame = await playhead.watch({
  url,
  detail: "single",
  start: 37,
  end: 37,
});

console.log(frame.sheets[0]?.url);   // one tile, 1560 px long edge

cURLbash

curl -X POST https://api.tryplayhead.com/v1/frames \
  -H "Authorization: Bearer $PLAYHEAD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "…", "detail": "single", "start": 37, "end": 37}'

Watch out for

Everything the API can refuse, and what to send instead, is on the errors page.