Find the moment a lecturer says two key words

What was saidLectureVerified

0:58CC-BY-3.0 · Berkman Center (presenter: William Fisher)

Proof frames

Click a frame to seek

Tool calls

4 calls · agentic-video 0.3.1

transcribeimac · 95 ms

Arguments

{
  "source": "$CLIP"
}

Result

{
  "ok": true,
  "data": {
    "status": "in_progress",
    "requested_model_size": "tiny",
    "requested_model_cached": false,
    "transcription_status": "started",
    "retry_after_seconds": 15,
    "transcription_message": "The tiny transcription started in the background. About 0% done (estimate): 0 s elapsed of roughly 10 s. Retry in about 15 seconds.",
    "elapsed_sec": 0,
    "estimated_total_sec": 10,
    "estimated_percent": 0
  }
}

transcribeimac · 3 ms

Arguments

{
  "source": "$CLIP"
}

Result

{
  "ok": true,
  "data": {
    "status": "in_progress",
    "requested_model_size": "tiny",
    "requested_model_cached": false,
    "transcription_status": "in_progress",
    "retry_after_seconds": 15,
    "transcription_message": "A transcription for this video is already running. About 30% done (estimate): 3 s elapsed of roughly 10 s. Retry in about 15 seconds.",
    "elapsed_sec": 3,
    "estimated_total_sec": 10,
    "estimated_percent": 30
  }
}

transcribeimac · 3 ms

Arguments

{
  "source": "$CLIP"
}

Result

{
  "ok": true,
  "data": {
    "source_path": "~/hill/gallery/repo/cards/said-lecture/clip.mp4",
    "language": "en",
    "duration_sec": 58.016292,
    "segment_count": 16,
    "segments": [
      {
        "id": 1,
        "start_sec": 0,
        "end_sec": 2.1,
        "text": "by a fair amount of illustrative graphic",
        "start_timecode": "00:00:00.000",
        "end_timecode": "00:00:02.100",
        "confidence": 0.997
      },
      {
        "id": 2,
        "start_sec": 2.1,
        "end_sec": 5.26,
        "text": "and audiovisual materials, so it's best if you watch",
        "start_timecode": "00:00:02.100",
        "end_timecode": "00:00:05.260",
        "confidence": 0.997
      },
      {
        "id": 3,
        "start_sec": 5.26,
        "end_sec": 8.1,
        "text": "the recordings of the lectures on a computer",
        "start_timecode": "00:00:05.260",
        "end_timecode": "00:00:08.100",
        "confidence": 0.997
      },
      {
        "id": 4,
        "start_sec": 8.1,
        "end_sec": 10.34,
        "text": "or other device with a fair size screen.",
        "start_timecode": "00:00:08.100",
        "end_timecode": "00:00:10.340",
        "confidence": 0.997
      },
      {
        "id": 5,
        "start_sec": 11.46,
        "end_sec": 14.14,
        "text": "The most important of those supplementary materials",
        "start_timecode": "00:00:11.460",
        "end_timecode": "00:00:14.140",
        "confidence": 0.997
      },
      {
        "id": 6,
        "start_sec": 14.14,
        "end_sec": 16.42,
        "text": "will consist of two maps that I've prepared",
        "start_timecode": "00:00:14.140",
        "end_timecode": "00:00:16.420",
        "confidence": 0.997
      },
      {
        "id": 7,
        "start_sec": 16.42,
        "end_sec": 19.3,
        "text": "using the mind manager software program.",
        "start_timecode": "00:00:16.420",
        "end_timecode": "00:00:19.300",
        "confidence": 0.997
      },
      {
        "id": 8,
        "start_sec": 20.3,
        "end_sec": 22.58,
        "text": "The map that will accompany this particular lecture",
        "start_timecode": "00:00:20.300",
        "end_timecode": "00:00:22.580",
        "confidence": 0.997
      },
      {
        "id": 9,
        "start_sec": 22.58,
        "end_sec": 25.26,
        "text": "is called Theories of IP,",
        "start_timecode": "00:00:22.580",
        "end_timecode": "00:00:25.260",
        "confidence": 0.997
      },
      {
        "id": 10,
        "start_sec": 25.26,
        "end_sec": 26.78,
        "text": "which says I'm sure you know by now",
        "start_timecode": "00:00:25.260",
        "end_timecode": "00:00:26.780",
        "confidence": 0.997
      },
      {
        "id": 11,
        "start_sec": 26.78,
        "end_sec": 34.33,
        "text": "the customary abbreviation for intellectual property. The heart of the map is shown on your screen now.",
        "start_timecode": "00:00:26.780",
        "end_timecode": "00:00:34.330",
        "confidence": 0.955
      },
      {
        "id": 12,
        "start_sec": 35.69,
        "end_sec": 40.89,
        "text": "I'll be displaying the native version of the map during this lecture, but I've also prepared",
        "start_timecode": "00:00:35.690",
        "end_timecode": "00:00:40.890",
        "confidence": 0.955
      },
      {
        "id": 13,
        "start_sec": 40.89,
        "end_sec": 48.97,
        "text": "a read-only PDF version, which can be downloaded from my homepage, the address of which is tfisher.org,",
        "start_timecode": "00:00:40.890",
        "end_timecode": "00:00:48.970",
        "confidence": 0.955
      },
      {
        "id": 14,
        "start_sec": 48.97,
        "end_sec": 53.97,
        "text": "that's TFISHR.org.",
        "start_timecode": "00:00:48.970",
        "end_timecode": "00:00:53.970",
        "confidence": 0.974
      },
      {
        "id": 15,
        "start_sec": 53.97,
        "end_sec": 56.97,
        "text": "Because I modify the map frequently,",
        "start_timecode": "00:00:53.970",
        "end_timecode": "00:00:56.970",
        "confidence": 0.974
      },
      {
        "id": 16,
        "start_sec": 56.97,
        "end_sec": 58.97,
        "text": "if you find it useful in the future.",
        "start_timecode": "00:00:56.970",
        "end_timecode": "00:00:58.970",
        "confidence": 0.974
      }
    ],
    "has_speech": true,
    "notice": "Note: Non-speech audio (music, sound effects, alarms) is NOT transcribed.",
    "confidence": 0.985,
    "uncertainty": "Whisper confidence is a no_speech_prob proxy; transcript content and alignment remain model-dependent."
  }
}

search_transcriptimac · 2 ms

Arguments

{
  "source": "$CLIP",
  "query": "accompany particular",
  "mode": "lexical",
  "top_k": 5
}

Result

{
  "ok": true,
  "data": {
    "hits": [
      {
        "segment_id": 8,
        "start_sec": 20.3,
        "end_sec": 22.58,
        "text": "The map that will accompany this particular lecture",
        "score": 1,
        "start_timecode": "00:00:20.300",
        "end_timecode": "00:00:22.580",
        "context": "The map that will accompany this particular lecture"
      }
    ],
    "total": 1
  }
}

Question and answer

Question: When does the speaker say "accompany particular"?
Answer: A keyword search for "accompany particular" first finds it 20.3 seconds into the clip.

Check passedanswer 20.3, expected 20.27 ±3.0

How it was checked

Truth from: captions
Fixed at: 2026-10-30 19:33

Made from the human captions published with the source (captions.vtt): the first caption line that starts at or after 20 s, ends inside the source, and has at least 6 words and 2 different words of 5 or more letters starts at 22.270 s of the source. The clip starts at 2.000 s of the source, so the line starts at 20.270 s in the clip; the truth is that time with a 3 s tolerance. No tool made this truth.

Keyword search only: the tool matched the words in its own speech-to-text, not their meaning. The clip is cut from a published video around one caption line, so the card checks that line only.

Try it yourself

Use agentic-video to find when my video says the words "accompany particular". Transcribe the video first, then search its transcript for those words in keyword mode (mode lexical), and tell me the start time of the first match in seconds. Use my own file.

Get the .mcpb file and open it in Claude Desktop.
Or: pip install agentic-video

Clip and licence

Licence: CC-BY-3.0
Author: Berkman Center (presenter: William Fisher)
Source: commons.wikimedia.org

This file is licensed under the Creative Commons Attribution 3.0 Unported license.