Find where the sound suddenly gets loud
0:18CC-BY-3.0 · Blender Foundation (Durian Open Movie project)
Proof frames
Tool calls
loudness_timeline
Arguments
{
"source": "$CLIP",
"start_sec": 0,
"end_sec": 4,
"window_sec": 2
}
Result
{
"ok": true,
"data": {
"source_path": "~/hill/gallery/tmp/R-loud/cards/loud-film/clip.mp4",
"start_sec": 0,
"end_sec": 4,
"window_sec": 2,
"bpm": null,
"silence_threshold_dbfs": -60,
"peak_dbfs": -28.817,
"peak_sec": 2.524,
"windows": [
{
"start_sec": 0,
"end_sec": 2,
"rms_dbfs": -47.797,
"peak_dbfs": -31.144,
"band_db": {
"sub": -55.584,
"low_mid": -53.624,
"mid": -77.215,
"high": -103.631,
"air": -111.588
},
"spectral_centroid_hz": 145.456,
"silent": false
},
{
"start_sec": 2,
"end_sec": 4,
"rms_dbfs": -42.264,
"peak_dbfs": -28.817,
"band_db": {
"sub": -47.99,
"low_mid": -42.546,
"mid": -61.348,
"high": -89.059,
"air": -99.549
},
"spectral_centroid_hz": 187.475,
"silent": false
}
],
"outliers": [
{
"start_sec": 0,
"end_sec": 2,
"band": "low_mid",
"direction": "cut",
"energy_db": -53.624,
"baseline_db": -42.546,
"delta_db": -11.078,
"min_delta_db": -11.078,
"max_delta_db": -11.078,
"energy_start_db": -53.624,
"energy_end_db": -53.624,
"entry_jump_db": null,
"exit_jump_db": -11.078,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 0,
"end_sec": 2,
"band": "mid",
"direction": "cut",
"energy_db": -77.215,
"baseline_db": -61.348,
"delta_db": -15.867,
"min_delta_db": -15.867,
"max_delta_db": -15.867,
"energy_start_db": -77.215,
"energy_end_db": -77.215,
"entry_jump_db": null,
"exit_jump_db": -15.867,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 0,
"end_sec": 2,
"band": "sub",
"direction": "cut",
"energy_db": -55.584,
"baseline_db": -47.99,
"delta_db": -7.594,
"min_delta_db": -7.594,
"max_delta_db": -7.594,
"energy_start_db": -55.584,
"energy_end_db": -55.584,
"entry_jump_db": null,
"exit_jump_db": -7.594,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 2,
"end_sec": 4,
"band": "low_mid",
"direction": "boost",
"energy_db": -42.546,
"baseline_db": -53.624,
"delta_db": 11.078,
"min_delta_db": 11.078,
"max_delta_db": 11.078,
"energy_start_db": -42.546,
"energy_end_db": -42.546,
"entry_jump_db": 11.078,
"exit_jump_db": null,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 2,
"end_sec": 4,
"band": "mid",
"direction": "boost",
"energy_db": -61.348,
"baseline_db": -77.215,
"delta_db": 15.867,
"min_delta_db": 15.867,
"max_delta_db": 15.867,
"energy_start_db": -61.348,
"energy_end_db": -61.348,
"entry_jump_db": 15.867,
"exit_jump_db": null,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 2,
"end_sec": 4,
"band": "sub",
"direction": "boost",
"energy_db": -47.99,
"baseline_db": -55.584,
"delta_db": 7.594,
"min_delta_db": 7.594,
"max_delta_db": 7.594,
"energy_start_db": -47.99,
"energy_end_db": -47.99,
"entry_jump_db": 7.594,
"exit_jump_db": null,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
}
],
"ignore_ranges": [],
"silence_gaps": [
{
"start_sec": 0,
"end_sec": 0.95,
"duration_sec": 0.95,
"threshold_dbfs": -60
},
{
"start_sec": 0.96,
"end_sec": 1,
"duration_sec": 0.04,
"threshold_dbfs": -60
},
{
"start_sec": 1.02,
"end_sec": 1.06,
"duration_sec": 0.04,
"threshold_dbfs": -60
}
],
"total": 2
}
}
loudness_timeline
Arguments
{
"source": "$CLIP",
"start_sec": 4,
"end_sec": 8,
"window_sec": 2
}
Result
{
"ok": true,
"data": {
"source_path": "~/hill/gallery/tmp/R-loud/cards/loud-film/clip.mp4",
"start_sec": 4,
"end_sec": 8,
"window_sec": 2,
"bpm": null,
"silence_threshold_dbfs": -60,
"peak_dbfs": -14.562,
"peak_sec": 5.94,
"windows": [
{
"start_sec": 4,
"end_sec": 6,
"rms_dbfs": -27.749,
"peak_dbfs": -14.562,
"band_db": {
"sub": -29.744,
"low_mid": -29.489,
"mid": -48.704,
"high": -68.536,
"air": -82.007
},
"spectral_centroid_hz": 133.193,
"silent": false
},
{
"start_sec": 6,
"end_sec": 8,
"rms_dbfs": -30.555,
"peak_dbfs": -16.869,
"band_db": {
"sub": -36.612,
"low_mid": -31.03,
"mid": -37.88,
"high": -57.539,
"air": -71.93
},
"spectral_centroid_hz": 294.428,
"silent": false
}
],
"outliers": [
{
"start_sec": 4,
"end_sec": 6,
"band": "air",
"direction": "cut",
"energy_db": -82.007,
"baseline_db": -71.93,
"delta_db": -10.077,
"min_delta_db": -10.077,
"max_delta_db": -10.077,
"energy_start_db": -82.007,
"energy_end_db": -82.007,
"entry_jump_db": null,
"exit_jump_db": -10.077,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 4,
"end_sec": 6,
"band": "high",
"direction": "cut",
"energy_db": -68.536,
"baseline_db": -57.539,
"delta_db": -10.997,
"min_delta_db": -10.997,
"max_delta_db": -10.997,
"energy_start_db": -68.536,
"energy_end_db": -68.536,
"entry_jump_db": null,
"exit_jump_db": -10.997,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 4,
"end_sec": 6,
"band": "mid",
"direction": "cut",
"energy_db": -48.704,
"baseline_db": -37.88,
"delta_db": -10.824,
"min_delta_db": -10.824,
"max_delta_db": -10.824,
"energy_start_db": -48.704,
"energy_end_db": -48.704,
"entry_jump_db": null,
"exit_jump_db": -10.824,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 4,
"end_sec": 6,
"band": "sub",
"direction": "boost",
"energy_db": -29.744,
"baseline_db": -36.612,
"delta_db": 6.868,
"min_delta_db": 6.868,
"max_delta_db": 6.868,
"energy_start_db": -29.744,
"energy_end_db": -29.744,
"entry_jump_db": null,
"exit_jump_db": 6.868,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 6,
"end_sec": 8,
"band": "air",
"direction": "boost",
"energy_db": -71.93,
"baseline_db": -82.007,
"delta_db": 10.077,
"min_delta_db": 10.077,
"max_delta_db": 10.077,
"energy_start_db": -71.93,
"energy_end_db": -71.93,
"entry_jump_db": 10.077,
"exit_jump_db": null,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
"…trimmed 3 more"
],
"ignore_ranges": [],
"silence_gaps": [],
"total": 2
}
}
loudness_timeline
Arguments
{
"source": "$CLIP",
"start_sec": 8,
"end_sec": 12,
"window_sec": 2
}
Result
{
"ok": true,
"data": {
"source_path": "~/hill/gallery/tmp/R-loud/cards/loud-film/clip.mp4",
"start_sec": 8,
"end_sec": 12,
"window_sec": 2,
"bpm": null,
"silence_threshold_dbfs": -60,
"peak_dbfs": -11.354,
"peak_sec": 8.956,
"windows": [
{
"start_sec": 8,
"end_sec": 10,
"rms_dbfs": -22.797,
"peak_dbfs": -11.354,
"band_db": {
"sub": -21.822,
"low_mid": -28.166,
"mid": -32.444,
"high": -38.018,
"air": -45.595
},
"spectral_centroid_hz": 325.932,
"silent": false
},
{
"start_sec": 10,
"end_sec": 12,
"rms_dbfs": -29.419,
"peak_dbfs": -16.802,
"band_db": {
"sub": -33.231,
"low_mid": -50.244,
"mid": -39.292,
"high": -82.547,
"air": -91.851
},
"spectral_centroid_hz": 161.106,
"silent": false
}
],
"outliers": [
{
"start_sec": 8,
"end_sec": 10,
"band": "high",
"direction": "boost",
"energy_db": -38.018,
"baseline_db": -82.547,
"delta_db": 44.529,
"min_delta_db": 44.529,
"max_delta_db": 44.529,
"energy_start_db": -38.018,
"energy_end_db": -38.018,
"entry_jump_db": null,
"exit_jump_db": 44.529,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 8,
"end_sec": 10,
"band": "low_mid",
"direction": "boost",
"energy_db": -28.166,
"baseline_db": -50.244,
"delta_db": 22.078,
"min_delta_db": 22.078,
"max_delta_db": 22.078,
"energy_start_db": -28.166,
"energy_end_db": -28.166,
"entry_jump_db": null,
"exit_jump_db": 22.078,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 8,
"end_sec": 10,
"band": "mid",
"direction": "boost",
"energy_db": -32.444,
"baseline_db": -39.292,
"delta_db": 6.848,
"min_delta_db": 6.848,
"max_delta_db": 6.848,
"energy_start_db": -32.444,
"energy_end_db": -32.444,
"entry_jump_db": null,
"exit_jump_db": 6.848,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 8,
"end_sec": 10,
"band": "sub",
"direction": "boost",
"energy_db": -21.822,
"baseline_db": -33.231,
"delta_db": 11.409,
"min_delta_db": 11.409,
"max_delta_db": 11.409,
"energy_start_db": -21.822,
"energy_end_db": -21.822,
"entry_jump_db": null,
"exit_jump_db": 11.409,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 10,
"end_sec": 12,
"band": "high",
"direction": "cut",
"energy_db": -82.547,
"baseline_db": -38.018,
"delta_db": -44.529,
"min_delta_db": -44.529,
"max_delta_db": -44.529,
"energy_start_db": -82.547,
"energy_end_db": -82.547,
"entry_jump_db": -44.529,
"exit_jump_db": null,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
"…trimmed 3 more"
],
"ignore_ranges": [],
"silence_gaps": [],
"total": 2
}
}
loudness_timeline
Arguments
{
"source": "$CLIP",
"start_sec": 12,
"end_sec": 16,
"window_sec": 2
}
Result
{
"ok": true,
"data": {
"source_path": "~/hill/gallery/tmp/R-loud/cards/loud-film/clip.mp4",
"start_sec": 12,
"end_sec": 16,
"window_sec": 2,
"bpm": null,
"silence_threshold_dbfs": -60,
"peak_dbfs": -12.541,
"peak_sec": 15.934,
"windows": [
{
"start_sec": 12,
"end_sec": 14,
"rms_dbfs": -30.429,
"peak_dbfs": -17.528,
"band_db": {
"sub": -31.836,
"low_mid": -32.83,
"mid": -37.204,
"high": -53.278,
"air": -63.419
},
"spectral_centroid_hz": 273.282,
"silent": false
},
{
"start_sec": 14,
"end_sec": 16,
"rms_dbfs": -22.646,
"peak_dbfs": -12.541,
"band_db": {
"sub": -59.991,
"low_mid": -27.2,
"mid": -23.096,
"high": -59.717,
"air": -69.944
},
"spectral_centroid_hz": 634.002,
"silent": false
}
],
"outliers": [
{
"start_sec": 12,
"end_sec": 14,
"band": "air",
"direction": "boost",
"energy_db": -63.419,
"baseline_db": -69.944,
"delta_db": 6.525,
"min_delta_db": 6.525,
"max_delta_db": 6.525,
"energy_start_db": -63.419,
"energy_end_db": -63.419,
"entry_jump_db": null,
"exit_jump_db": 6.525,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 12,
"end_sec": 14,
"band": "high",
"direction": "boost",
"energy_db": -53.278,
"baseline_db": -59.717,
"delta_db": 6.439,
"min_delta_db": 6.439,
"max_delta_db": 6.439,
"energy_start_db": -53.278,
"energy_end_db": -53.278,
"entry_jump_db": null,
"exit_jump_db": 6.439,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 12,
"end_sec": 14,
"band": "mid",
"direction": "cut",
"energy_db": -37.204,
"baseline_db": -23.096,
"delta_db": -14.108,
"min_delta_db": -14.108,
"max_delta_db": -14.108,
"energy_start_db": -37.204,
"energy_end_db": -37.204,
"entry_jump_db": null,
"exit_jump_db": -14.108,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 12,
"end_sec": 14,
"band": "sub",
"direction": "boost",
"energy_db": -31.836,
"baseline_db": -59.991,
"delta_db": 28.155,
"min_delta_db": 28.155,
"max_delta_db": 28.155,
"energy_start_db": -31.836,
"energy_end_db": -31.836,
"entry_jump_db": null,
"exit_jump_db": 28.155,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
{
"start_sec": 14,
"end_sec": 16,
"band": "air",
"direction": "cut",
"energy_db": -69.944,
"baseline_db": -63.419,
"delta_db": -6.525,
"min_delta_db": -6.525,
"max_delta_db": -6.525,
"energy_start_db": -69.944,
"energy_end_db": -69.944,
"entry_jump_db": -6.525,
"exit_jump_db": null,
"internal_range_db": 0,
"trend_db": 0,
"monotonic_fraction": 0,
"shape": "transient",
"window_count": 1,
"fault_level": false,
"classification": "informational",
"ignored": false,
"ignore_reason": null
},
"…trimmed 3 more"
],
"ignore_ranges": [],
"silence_gaps": [],
"total": 2
}
}
Question and answer
- Question
- Where does it suddenly get loud?
- Answer
- The loudest 2-second stretch runs from 14 to 16 seconds, at -22.6 dB RMS, the loudest of the 8 windows across the clip.
Check passedIoU 1.00, minimum 0.5
How it was checked
- Truth from
- constructed
- Fixed at
Planted by this recipe before any tool ran: ffmpeg cut the first 18 s of the source (its loudest sample measured at 0.0 dBFS by volumedetect), the whole clip was first lowered 13.0 dB so the raised stretch peaks below full scale, and raised the sound from 14 s to 16 s by 12 dB with a volume filter (the picture is not changed). The truth is that stretch, 14 to 16 s, checked with an IoU of at least 0.5. The calls read 2-second windows that start at 0, 2, 4 and so on, so the planted stretch is the window 14 to 16 s.
A script raised the sound by 12 dB from 14 to 16 seconds, a planted change. To keep the raised stretch below full scale, the whole clip was first lowered 13.0 dB. The answer is the loudest 2-second window, so the card does not test timing finer than 2 seconds. Only the first 16 seconds of the source were analysed.
Try it yourself
Use agentic-video to find where the sound in my video suddenly gets loud. Run loudness_timeline on my file in 4-second ranges that cover the first 16 seconds, with a window of 2 seconds each time. Tell me the start and end of the loudest window across all the runs, and how loud it is compared with the windows around it.
- Get the .mcpb file and open it in Claude Desktop.
- Or:
pip install agentic-video
Clip and licence
- Licence
- CC-BY-3.0
- Author
- Blender Foundation (Durian Open Movie project)
- Source
- commons.wikimedia.org
This file is licensed under the Creative Commons Attribution 3.0 Unported license.