Find where the sound drops out for a moment
0:20generated · generated
Proof frames
Tool calls
loudness_timeline
Arguments
{
"source": "$CLIP",
"start_sec": 7.77,
"end_sec": 15.27,
"window_sec": 1
}
Result
{
"ok": true,
"data": {
"source_path": "~/work/cards/gap-synthetic/clip.mp4",
"start_sec": 7.77,
"end_sec": 15.27,
"window_sec": 1,
"bpm": null,
"silence_threshold_dbfs": -60,
"peak_dbfs": -26.353,
"peak_sec": 10.773,
"windows": [
{
"start_sec": 7.77,
"end_sec": 8.77,
"rms_dbfs": -27.103,
"peak_dbfs": -27.052,
"band_db": {
"sub": -120,
"low_mid": -25.747,
"mid": -90.11,
"high": -110.885,
"air": -109.491
},
"spectral_centroid_hz": 440,
"silent": false
},
{
"start_sec": 8.77,
"end_sec": 9.77,
"rms_dbfs": -27.107,
"peak_dbfs": -27.052,
"band_db": {
"sub": -120,
"low_mid": -25.753,
"mid": -88.11,
"high": -110.858,
"air": -109.667
},
"spectral_centroid_hz": 440,
"silent": false
},
{
"start_sec": 9.77,
"end_sec": 10.77,
"rms_dbfs": -27.104,
"peak_dbfs": -27.062,
"band_db": {
"sub": -120,
"low_mid": -25.751,
"mid": -90.348,
"high": -110.857,
"air": -109.659
},
"spectral_centroid_hz": 440,
"silent": false
},
{
"start_sec": 10.77,
"end_sec": 11.77,
"rms_dbfs": -52.041,
"peak_dbfs": -26.353,
"band_db": {
"sub": -120,
"low_mid": -120,
"mid": -120,
"high": -120,
"air": -120
},
"spectral_centroid_hz": 906.568,
"silent": false
},
{
"start_sec": 11.77,
"end_sec": 12.77,
"rms_dbfs": -30.273,
"peak_dbfs": -26.384,
"band_db": {
"sub": -74.853,
"low_mid": -29.208,
"mid": -53.983,
"high": -69.643,
"air": -74.026
},
"spectral_centroid_hz": 441.943,
"silent": false
},
{
"start_sec": 12.77,
"end_sec": 13.77,
"rms_dbfs": -27.102,
"peak_dbfs": -27.053,
"band_db": {
"sub": -120,
"low_mid": -25.747,
"mid": -91.152,
"high": -110.878,
"air": -109.589
},
"spectral_centroid_hz": 440.001,
"silent": false
},
{
"start_sec": 13.77,
"end_sec": 14.77,
"rms_dbfs": -27.104,
"peak_dbfs": -27.053,
"band_db": {
"sub": -120,
"low_mid": -25.754,
"mid": -91.733,
"high": -110.859,
"air": -109.614
},
"spectral_centroid_hz": 440,
"silent": false
},
{
"start_sec": 14.77,
"end_sec": 15.27,
"rms_dbfs": -27.103,
"peak_dbfs": -27.062,
"band_db": {
"sub": -120,
"low_mid": -25.749,
"mid": -92.453,
"high": -110.875,
"air": -109.666
},
"spectral_centroid_hz": 440,
"silent": false
}
],
"outliers": [
{
"start_sec": 8.77,
"end_sec": 9.77,
"band": "mid",
"direction": "cut",
"energy_db": -88.11,
"baseline_db": -53.983,
"delta_db": -34.127,
"min_delta_db": -34.127,
"max_delta_db": -34.127,
"energy_start_db": -88.11,
"energy_end_db": -88.11,
"entry_jump_db": 2,
"exit_jump_db": 2.238,
"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": 11.77,
"end_sec": 12.77,
"band": "mid",
"direction": "boost",
"energy_db": -53.983,
"baseline_db": -88.11,
"delta_db": 34.127,
"min_delta_db": 34.127,
"max_delta_db": 34.127,
"energy_start_db": -53.983,
"energy_end_db": -53.983,
"entry_jump_db": 66.017,
"exit_jump_db": 37.169,
"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": 10.78,
"end_sec": 12.28,
"duration_sec": 1.5,
"threshold_dbfs": -60
}
],
"total": 8
}
}
review_video
Arguments
{
"source": "$CLIP"
}
Result
{
"ok": true,
"data": {
"metadata": {
"source_path": "~/work/cards/gap-synthetic/clip.mp4",
"duration_sec": 20,
"width": 640,
"height": 360,
"fps": 25,
"format_name": "mov,mp4,m4a,3gp,3g2,mj2",
"size_bytes": 447674,
"has_audio": true,
"audio_codec": "aac",
"video_codec": "h264",
"fingerprint": "f3126f705ae994b624a9",
"has_video": true
},
"contact_sheet": {
"file_path": "<cache>/f3126f705ae994b624a9/contact_sheets/sheet_24samples_4cols_423fa4.jpg",
"sample_count": 24,
"rows": 6,
"cols": 4,
"start_sec": 0.417,
"end_sec": 19.583,
"timestamps": [
0.417,
1.25,
2.083,
2.917,
3.75,
4.583,
5.417,
6.25,
7.083,
7.917,
8.75,
9.583,
10.417,
11.25,
12.083,
12.917,
13.75,
14.583,
15.417,
16.25,
17.083,
17.917,
18.75,
19.583
],
"frame_width": 768,
"frame_height": 432,
"tool_file": {
"_tag": "ToolFile",
"name": "sheet_24samples_4cols_423fa4.jpg",
"mimeType": "image/jpeg",
"encoding": "base64",
"data": "<771240 base64 chars dropped>",
"byteLength": 578430
}
},
"cuts": [
{
"timestamp_sec": 10,
"score": 0.189111,
"kind": "cut"
}
],
"cuts_total": 1,
"loudness": {
"average_rms_dbfs": -27.503,
"peak_dbfs": -25.323,
"peak_sec": 0.004,
"window_sec": 0.25,
"silence_threshold_dbfs": -60,
"silence_gaps": [
{
"start_sec": 10.78,
"end_sec": 12.28,
"duration_sec": 1.5,
"threshold_dbfs": -60
}
],
"silence_gaps_total": 1,
"outliers_total": 9,
"fault_outliers_total": 0,
"outliers": [
{
"start_sec": 20,
"end_sec": 20.010667,
"band": "low_mid",
"direction": "cut",
"shape": "transient",
"delta_db": -54.345,
"fault_level": false
},
{
"start_sec": 10.75,
"end_sec": 11,
"band": "low_mid",
"direction": "cut",
"shape": "transient",
"delta_db": -35.159,
"fault_level": false
},
{
"start_sec": 12.25,
"end_sec": 12.5,
"band": "mid",
"direction": "boost",
"shape": "transient",
"delta_db": 26.027,
"fault_level": false
},
{
"start_sec": 10.75,
"end_sec": 11,
"band": "mid",
"direction": "boost",
"shape": "transient",
"delta_db": 17.969,
"fault_level": false
},
{
"start_sec": 10.75,
"end_sec": 11,
"band": "air",
"direction": "cut",
"shape": "transient",
"delta_db": -7.934,
"fault_level": false
},
{
"start_sec": 12.25,
"end_sec": 12.5,
"band": "air",
"direction": "boost",
"shape": "transient",
"delta_db": 7.934,
"fault_level": false
},
{
"start_sec": 10.75,
"end_sec": 11,
"band": "high",
"direction": "cut",
"shape": "transient",
"delta_db": -7.875,
"fault_level": false
},
{
"start_sec": 12.25,
"end_sec": 12.5,
"band": "high",
"direction": "boost",
"shape": "transient",
"delta_db": 7.875,
"fault_level": false
},
{
"start_sec": 0,
"end_sec": 0.25,
"band": "mid",
"direction": "boost",
"shape": "transient",
"delta_db": 7.766,
"fault_level": false
}
]
}
}
}
Question and answer
- Question
- Is there a silent gap in the sound? Where does it start and end?
- Answer
- The tool reports the longest silent gap in the sound, from 10.78 to 12.28 seconds, lasting 1.50 seconds.
Check passedIoU 0.99, minimum 0.7
How it was checked
- Truth from
- constructed
- Fixed at
Planted by this recipe: ffmpeg cut the first 20 s of the source and muted its sound (volume 0, so digital silence) from 10.77 s to 12.27 s, keeping the picture. The truth is that silent interval, 10.77 to 12.27 s. The call covers 7.77 to 15.27 s (the gap with 3 s either side). The answer is the longest silent gap loudness_timeline reports in that range. IoU tolerance 0.7.
A script muted 1.5 seconds of this clip's sound at a time it chose and left the picture alone. The answer is the one silent gap the tool reports in a 7.5-second range around it, so the card does not show every quiet moment in the clip.
Try it yourself
Use agentic-video to check the sound in my video for a silent gap. Call loudness_timeline on my file from 7.77 to 15.27 seconds, and tell me where the quiet part starts and ends. Then call review_video on my whole file and tell me what it reports about silence. Use my own file.
- Get the .mcpb file and open it in Claude Desktop.
- Or:
pip install agentic-video
Clip and licence
- Licence
- generated
Generated for the gallery; no third-party material.