Find where the sound suddenly gets loud
0:18CC0 · Mojmir Churavy
Proof frames
Tool calls
loudness_timeline
Arguments
{
"source": "$CLIP",
"start_sec": 0,
"end_sec": 4,
"window_sec": 2
}
Result
{
"ok": true,
"data": {
"source_path": "~/hill/gallery/tmp/R-loud/cards/loud-monitoring/clip.mp4",
"start_sec": 0,
"end_sec": 4,
"window_sec": 2,
"bpm": null,
"silence_threshold_dbfs": -60,
"peak_dbfs": -24.223,
"peak_sec": 3.924,
"windows": [
{
"start_sec": 0,
"end_sec": 2,
"rms_dbfs": -36.409,
"peak_dbfs": -24.681,
"band_db": {
"sub": -42.91,
"low_mid": -52.741,
"mid": -63.399,
"high": -70.525,
"air": -72.713
},
"spectral_centroid_hz": 83.131,
"silent": false
},
{
"start_sec": 2,
"end_sec": 4,
"rms_dbfs": -41.407,
"peak_dbfs": -24.223,
"band_db": {
"sub": -43.718,
"low_mid": -52.691,
"mid": -64.302,
"high": -70.59,
"air": -72.906
},
"spectral_centroid_hz": 110.65,
"silent": false
}
],
"outliers": [],
"ignore_ranges": [],
"silence_gaps": [
{
"start_sec": 0,
"end_sec": 0.2,
"duration_sec": 0.2,
"threshold_dbfs": -60
}
],
"total": 2
}
}
loudness_timeline
Arguments
{
"source": "$CLIP",
"start_sec": 4,
"end_sec": 8,
"window_sec": 2
}
Result
{
"ok": true,
"data": {
"source_path": "~/hill/gallery/tmp/R-loud/cards/loud-monitoring/clip.mp4",
"start_sec": 4,
"end_sec": 8,
"window_sec": 2,
"bpm": null,
"silence_threshold_dbfs": -60,
"peak_dbfs": -15.088,
"peak_sec": 7.035,
"windows": [
{
"start_sec": 4,
"end_sec": 6,
"rms_dbfs": -41.203,
"peak_dbfs": -29.192,
"band_db": {
"sub": -40.271,
"low_mid": -46.379,
"mid": -63.017,
"high": -70.224,
"air": -72.387
},
"spectral_centroid_hz": 99.703,
"silent": false
},
{
"start_sec": 6,
"end_sec": 8,
"rms_dbfs": -31.187,
"peak_dbfs": -15.088,
"band_db": {
"sub": -28.208,
"low_mid": -34.385,
"mid": -62.482,
"high": -69.983,
"air": -73.474
},
"spectral_centroid_hz": 91.989,
"silent": false
}
],
"outliers": [
{
"start_sec": 4,
"end_sec": 6,
"band": "low_mid",
"direction": "cut",
"energy_db": -46.379,
"baseline_db": -34.385,
"delta_db": -11.994,
"min_delta_db": -11.994,
"max_delta_db": -11.994,
"energy_start_db": -46.379,
"energy_end_db": -46.379,
"entry_jump_db": null,
"exit_jump_db": -11.994,
"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": "cut",
"energy_db": -40.271,
"baseline_db": -28.208,
"delta_db": -12.063,
"min_delta_db": -12.063,
"max_delta_db": -12.063,
"energy_start_db": -40.271,
"energy_end_db": -40.271,
"entry_jump_db": null,
"exit_jump_db": -12.063,
"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": "low_mid",
"direction": "boost",
"energy_db": -34.385,
"baseline_db": -46.379,
"delta_db": 11.994,
"min_delta_db": 11.994,
"max_delta_db": 11.994,
"energy_start_db": -34.385,
"energy_end_db": -34.385,
"entry_jump_db": 11.994,
"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": 6,
"end_sec": 8,
"band": "sub",
"direction": "boost",
"energy_db": -28.208,
"baseline_db": -40.271,
"delta_db": 12.063,
"min_delta_db": 12.063,
"max_delta_db": 12.063,
"energy_start_db": -28.208,
"energy_end_db": -28.208,
"entry_jump_db": 12.063,
"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": [],
"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-monitoring/clip.mp4",
"start_sec": 8,
"end_sec": 12,
"window_sec": 2,
"bpm": null,
"silence_threshold_dbfs": -60,
"peak_dbfs": -5.189,
"peak_sec": 11.56,
"windows": [
{
"start_sec": 8,
"end_sec": 10,
"rms_dbfs": -29.514,
"peak_dbfs": -16.059,
"band_db": {
"sub": -27.815,
"low_mid": -33.099,
"mid": -63.2,
"high": -71.01,
"air": -73.517
},
"spectral_centroid_hz": 87.551,
"silent": false
},
{
"start_sec": 10,
"end_sec": 12,
"rms_dbfs": -19.324,
"peak_dbfs": -5.189,
"band_db": {
"sub": -20.059,
"low_mid": -25.718,
"mid": -48.855,
"high": -58.303,
"air": -61.085
},
"spectral_centroid_hz": 90.545,
"silent": false
}
],
"outliers": [
{
"start_sec": 8,
"end_sec": 10,
"band": "air",
"direction": "cut",
"energy_db": -73.517,
"baseline_db": -61.085,
"delta_db": -12.432,
"min_delta_db": -12.432,
"max_delta_db": -12.432,
"energy_start_db": -73.517,
"energy_end_db": -73.517,
"entry_jump_db": null,
"exit_jump_db": -12.432,
"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": "high",
"direction": "cut",
"energy_db": -71.01,
"baseline_db": -58.303,
"delta_db": -12.707,
"min_delta_db": -12.707,
"max_delta_db": -12.707,
"energy_start_db": -71.01,
"energy_end_db": -71.01,
"entry_jump_db": null,
"exit_jump_db": -12.707,
"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": "cut",
"energy_db": -33.099,
"baseline_db": -25.718,
"delta_db": -7.381,
"min_delta_db": -7.381,
"max_delta_db": -7.381,
"energy_start_db": -33.099,
"energy_end_db": -33.099,
"entry_jump_db": null,
"exit_jump_db": -7.381,
"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": "cut",
"energy_db": -63.2,
"baseline_db": -48.855,
"delta_db": -14.345,
"min_delta_db": -14.345,
"max_delta_db": -14.345,
"energy_start_db": -63.2,
"energy_end_db": -63.2,
"entry_jump_db": null,
"exit_jump_db": -14.345,
"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": "cut",
"energy_db": -27.815,
"baseline_db": -20.059,
"delta_db": -7.756,
"min_delta_db": -7.756,
"max_delta_db": -7.756,
"energy_start_db": -27.815,
"energy_end_db": -27.815,
"entry_jump_db": null,
"exit_jump_db": -7.756,
"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 5 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-monitoring/clip.mp4",
"start_sec": 12,
"end_sec": 16,
"window_sec": 2,
"bpm": null,
"silence_threshold_dbfs": -60,
"peak_dbfs": -19.288,
"peak_sec": 14.643,
"windows": [
{
"start_sec": 12,
"end_sec": 14,
"rms_dbfs": -37.53,
"peak_dbfs": -22.096,
"band_db": {
"sub": -38.818,
"low_mid": -48.781,
"mid": -60.593,
"high": -69.353,
"air": -71.42
},
"spectral_centroid_hz": 92.82,
"silent": false
},
{
"start_sec": 14,
"end_sec": 16,
"rms_dbfs": -34.18,
"peak_dbfs": -19.288,
"band_db": {
"sub": -32.046,
"low_mid": -38.43,
"mid": -62.606,
"high": -69.491,
"air": -72.087
},
"spectral_centroid_hz": 84.368,
"silent": false
}
],
"outliers": [
{
"start_sec": 12,
"end_sec": 14,
"band": "low_mid",
"direction": "cut",
"energy_db": -48.781,
"baseline_db": -38.43,
"delta_db": -10.351,
"min_delta_db": -10.351,
"max_delta_db": -10.351,
"energy_start_db": -48.781,
"energy_end_db": -48.781,
"entry_jump_db": null,
"exit_jump_db": -10.351,
"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": "cut",
"energy_db": -38.818,
"baseline_db": -32.046,
"delta_db": -6.772,
"min_delta_db": -6.772,
"max_delta_db": -6.772,
"energy_start_db": -38.818,
"energy_end_db": -38.818,
"entry_jump_db": null,
"exit_jump_db": -6.772,
"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": "low_mid",
"direction": "boost",
"energy_db": -38.43,
"baseline_db": -48.781,
"delta_db": 10.351,
"min_delta_db": 10.351,
"max_delta_db": 10.351,
"energy_start_db": -38.43,
"energy_end_db": -38.43,
"entry_jump_db": 10.351,
"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": 14,
"end_sec": 16,
"band": "sub",
"direction": "boost",
"energy_db": -32.046,
"baseline_db": -38.818,
"delta_db": 6.772,
"min_delta_db": 6.772,
"max_delta_db": 6.772,
"energy_start_db": -32.046,
"energy_end_db": -32.046,
"entry_jump_db": 6.772,
"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": [],
"total": 2
}
}
Question and answer
- Question
- Where does it suddenly get loud?
- Answer
- The loudest 2-second stretch runs from 10 to 12 seconds, at -19.3 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 -15.1 dBFS by volumedetect), the whole clip needed no lowering to keep the raised stretch below full scale, and raised the sound from 10 s to 12 s by 12 dB with a volume filter (the picture is not changed). The truth is that stretch, 10 to 12 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 10 to 12 s.
A script raised the sound by 12 dB from 10 to 12 seconds, a planted change. 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
- CC0
- Author
- Mojmir Churavy
- Source
- commons.wikimedia.org
This file is made available under the Creative Commons CC0 1.0 Universal Public Domain Dedication.