{ "file": "references/0258.wav", "sample_rate_for_analysis": 16000, "duration_sec": 11.102, "voiced_fraction": 0.68, "pause_map": [ { "start": 0.92, "end": 1.28, "duration": 0.36 }, { "start": 2.93, "end": 3.77, "duration": 0.84 }, { "start": 5.6, "end": 6.37, "duration": 0.77 }, { "start": 7.32, "end": 7.55, "duration": 0.23 }, { "start": 8.74, "end": 9.24, "duration": 0.5 } ], "f0_hz": { "median": 151.066, "p10_p90": [ 67.292, 207.558 ], "contour_20_points": [ 216.12, 146.77, 68.41, 167.51, 148.47, 137.67, 167.67, 192.57, 138.53, 216.32, 65.37, 194.78, 219.67, 221.17, 159.71, 108.39, 156.23, 155.19, 130.75, 168.59 ] }, "energy_db": { "p10_p50_p90": [ -50.311, -14.593, -7.248 ], "dynamic_range_db": 43.063, "contour_20_points": [ -68.53, -7.02, -47.14, -5.05, -9.03, -34.79, -84.79, -10.82, -7.72, -17.51, -48.82, -7.79, -8.61, -10.14, -24.11, -42.31, -7.21, -7.5, -16.64, -45.91 ] }, "timbral_proxies": { "spectral_centroid_hz_median": 1341.756, "spectral_flatness_median": 0.004 }, "interpretation": { "target": "soft, close-mic, restrained mechanical delivery", "sarcasm": "low-to-moderate pitch movement with deliberate clause-final timing", "smile": "look for local energy/brightness lift around emphasized words; do not synthesize a broad cheerful smile" }, "text": "Отлично. А вот и результаты теста: вы ужасный человек. Я серьёзно, именно так здесь и написано: ужасный человек. Мы даже не проверяли это.", "text_chars_per_sec": 12.43, "source": { "file": "sources_silero/0258.wav", "sample_rate_for_analysis": 16000, "duration_sec": 9.0, "voiced_fraction": 0.714, "pause_map": [ { "start": 2.08, "end": 2.37, "duration": 0.29 }, { "start": 3.44, "end": 3.53, "duration": 0.09 }, { "start": 4.3, "end": 4.43, "duration": 0.13 }, { "start": 5.88, "end": 6.19, "duration": 0.31 }, { "start": 7.13, "end": 7.53, "duration": 0.4 } ], "f0_hz": { "median": 201.649, "p10_p90": [ 169.566, 228.973 ], "contour_20_points": [ 234.33, 202.98, 251.83, 211.06, 207.02, 262.45, 233.4, 158.6, 216.32, 176.51, 196.76, 200.8, 173.27, 200.04, 196.51, 170.81, 213.51, 206.36, 169.93, 168.59 ] }, "energy_db": { "p10_p50_p90": [ -59.701, -22.969, -14.064 ], "dynamic_range_db": 45.637, "contour_20_points": [ -82.8, -28.53, -11.42, -14.71, -54.51, -39.98, -37.88, -28.97, -14.0, -29.0, -26.98, -24.18, -26.0, -80.7, -22.61, -39.82, -17.19, -32.76, -29.57, -85.14 ] }, "timbral_proxies": { "spectral_centroid_hz_median": 1494.706, "spectral_flatness_median": 0.006 }, "interpretation": { "target": "soft, close-mic, restrained mechanical delivery", "sarcasm": "low-to-moderate pitch movement with deliberate clause-final timing", "smile": "look for local energy/brightness lift around emphasized words; do not synthesize a broad cheerful smile" }, "text": "Отлично. А вот и результаты теста: вы ужасный человек. Я серьёзно, именно так здесь и написано: ужасный человек. Мы даже не проверяли это.", "text_chars_per_sec": 15.333 }, "pipeline_control": { "tts_text": "Отлично. А вот и результаты теста: вы ужасный человек. Я серьёзно, именно так здесь и написано: ужасный человек. Мы даже не проверяли это.", "duration_stage": "pre", "speaker_reference": "0258" } }