Tour a 5-section music montage and find each section start
Proof frames
Tool calls
overview_chunks
Arguments
{
"source": "$CLIP",
"chunk_sec": 60,
"samples_per_chunk": 8
}
Result
{
"ok": true,
"data": {
"chunks": [
{
"file_path": "/private<cache>/fdbcf4ec7f1d68febef2/contact_sheets/sheet_8samples_4cols_f1fffd.jpg",
"sample_count": 8,
"rows": 2,
"cols": 4,
"start_sec": 2.4825,
"end_sec": 37.2375,
"timestamps": [
2.4825,
7.4475,
12.4125,
17.377499999999998,
22.3425,
27.307499999999997,
32.2725,
37.2375
],
"frame_width": 768,
"frame_height": 432,
"index": 1,
"range_start_sec": 0,
"range_end_sec": 39.72,
"tool_file": {
"_tag": "ToolFile",
"name": "sheet_8samples_4cols_f1fffd.jpg",
"mimeType": "image/jpeg",
"encoding": "base64",
"data": "<502576 base64 chars dropped>",
"byteLength": 376930
}
}
],
"total": 1,
"start_sec": 0,
"end_sec": 39.72,
"chunk_sec": 60
}
}
detect_cuts
Arguments
{
"source": "$CLIP"
}
Result
{
"ok": true,
"data": {
"cuts": [
{
"timestamp_sec": 7.16,
"score": 0.686258,
"kind": "cut"
},
{
"timestamp_sec": 15.12,
"score": 0.766405,
"kind": "cut"
},
{
"timestamp_sec": 18.95,
"score": 0.077132,
"kind": "transition"
},
{
"timestamp_sec": 21.9,
"score": 0.090878,
"kind": "transition"
},
{
"timestamp_sec": 24.96,
"score": 0.801828,
"kind": "cut"
},
{
"timestamp_sec": 32.88,
"score": 0.472584,
"kind": "cut"
}
],
"total": 6
}
}
Question and answer
- Question
- Give me a quick tour of this video. Where do the sections start?
- Answer
- detect_cuts lists 6 changes, at 7.16, 15.12, 18.95, 21.9, 24.96, 32.88 seconds.
- Tool returned
- [7.16,15.12,18.95,21.9,24.96,32.88]
- Truth
- [7.12,15.04,24.84,32.72]
How it was checked
- Truth from
- constructed
- Fixed at
Planted by this recipe before any tool ran: ffmpeg joined 5 sections with hard cuts and no sound, in this order: andy-russell-drum-solo-1945, imanuel-piano, street-musicians-new-arbat, street-drummer-portland, brian-silas-piano-bhopal. The sections start at 67.72 s, 110.48 s, 16.84 s, 29.48 s, 28.52 s in their sources and are 7.12, 7.92, 9.8, 7.88, 7 s long (no scene change above 0.3 inside any section). The truth is the planted join times 7.12 s, 15.04 s, 24.84 s, 32.72 s, the start of each section after the first, with tolerance 0.5 s. The calls are overview_chunks over the whole montage as one sheet, then detect_cuts with its default threshold, both fixed before the run.
A script joined 5 sections, each from a different clip of the same kind, with hard cuts and no sound, so the answer is the planted joins and not a real film's structure. The first section's start (0 s) is not counted.
Try it yourself
Using agentic-video, give me a quick tour of my video. Run overview_chunks on the whole video to see its sections, then run detect_cuts on the whole video and tell me the time of each section start, 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
- CC0
- Author
- B.G. DeSylva Productions Inc
- Source
- commons.wikimedia.org
This file is made available under the Creative Commons CC0 1.0 Universal Public Domain Dedication.
Also uses (insert 1)
- Licence
- CC-BY-SA-4.0
- Author
- PoseidonSports
- Source
- commons.wikimedia.org
This file is licensed under the Creative Commons Attribution-Share Alike 4.0 International license.
Also uses (insert 2)
- Licence
- CC-BY-4.0
- Author
- Predatorsamsung
- Source
- commons.wikimedia.org
This file is licensed under the Creative Commons Attribution 4.0 International license.
Also uses (insert 3)
- Licence
- PD
- Author
- Kingofthedead
- Source
- commons.wikimedia.org
I, the copyright holder of this work, release this work into the public domain.
Also uses (insert 4)
- Licence
- CC-BY-SA-4.0
- Author
- Suyash Dwivedi
- Source
- commons.wikimedia.org
This file is licensed under the Creative Commons Attribution-Share Alike 4.0 International license.