← Back to directory

Split audio into speech, music, silence and noise segments with start/end times,...

https://ton.halowerk.com/v1/speech-music-segment

Overview

Split audio into speech, music, silence and noise segments with start/end times, using disclosed signal features and rules (no model). Decodes up to 10 minutes (mono, 16 kHz). Frame features (64 ms, 20 ms hop): energy, spectral flatness 100–6000 Hz, periodicity as Boersma (1993) window-corrected autocorrelation (70–500 Hz) and zero-crossing rate.

Protocol x402 (POST)
Price $0.0050
Payment Asset USD Coin
Payment Network eip155:8453
Category uncategorized
Provider ton
Source bazaar
Indexed 2026-11-21 08:10:21

Health

Status unknown
Latency (p50) —
Uptime (30d) —
Reliability Score —
Last Checked Never
Last Healthy Never
Consecutive Failures 0

x402 Payment Validation

Payment Requirements —
Asset Verified —
Facilitator —

Input Schema

{ "body": { "audio_url": "https://ton.halowerk.com/beispiel/speech-music-segment-audio.ogg", "include_windows": true }, "bodyType": "json", "method": "POST", "type": "http" }

Output Schema

{ "example": { "limitations": [ "Rule thresholds were checked on clean synthetic speech and music; speech over music is labelled by the dominant class.", "Singing is usually labelled music; unpitched percussion without tonal instruments is labelled noise.", "Window resolution is 0.5 s; boundaries are accurate to about 0.5 s." ], "result": { "rules": [ "silence: level < -55 dBFS or more than 45 dB below the 95th-percentile window level", "noise: flatness >= 0.25, periodicity < 0.5 and pitch-grid concentration < 0.6", "music: pitch-grid concentration >= 0.7, or >= 0.5 without speech-like cues", "speech: low-energy ratio >= 0.25, high-ZCR ratio >= 0.1 or >= 3 voicing changes per second", "otherwise: noise (other sound)", "then 3-window median and merging of segments shorter than 1 s" ], "segments": [ { "duration_s": 6.63, "end_s": 6.63, "start_s": 0, "type": "speech" } ], "source": { "analysed_s": 6.625, "analysis_rate_hz": 16000, "bytes": 26328, "channels": 1, "codec": "opus", "container": "ogg", "duration_s": 6.632, "sample_rate": 48000, "sha256": "01ff5cfd61fb876b4222d6a73debfeb3c844d0bb8ec1a28eb218a588eb364ba2" }, "totals_s": { "music": 0, "noise": 0, "silence": 0, "speech": 6.63 }, "windows": [ { "flatness": 0, "high_zcr_ratio": 0.18, "label": "speech", "level_db": -11.5, "low_energy_ratio": 0.4, "periodicity": 0.975, "pitch_grid_concentration": 0.064, "start_s": 0, "voiced": 1, "voicing_changes_per_s": 0 }, { "flatness": 0.001, "high_zcr_ratio": 0.28, "label": "speech", "level_db": -12, "low_energy_ratio": 0.46, "periodicity": 0.962, "pitch_grid_concentration": 0.112, "start_s": 0.5, "voiced": 1, "voicing_changes_per_s": 0 }, { "flatness": 0.001, "high_zcr_ratio": 0.26, "label": "speech", "level_db": -14, "low_energy_ratio": 0.34, "periodicity": 0.952, "pitch_grid_concentration": 0.436, "start_s": 1, "voiced": 1, "voicing_changes_per_s": 0 }, { "flatness": 0.001, "high_zcr_ratio": 0.12, "label": "speech", "level_db": -12.4, "low_energy_ratio": 0.26, "periodicity": 0.969, "pitch_grid_concentration": 0.506, "start_s": 1.5, "voiced": 1, "voicing_changes_per_s": 0 }, { "flatness": 0.001, "high_zcr_ratio": 0.14, "label": "speech", "level_db": -13.1, "low_energy_ratio": 0.38, "periodicity": 0.971, "pitch_grid_concentration": 0.291, "start_s": 2, "voiced": 1, "voicing_changes_per_s": 0 }, { "flatness": 0.002, "high_zcr_ratio": 0.16, "label": "speech", "level_db": -14.7, "low_energy_ratio": 0.36, "periodicity": 0.973, "pitch_grid_concentration": 0.348, "start_s": 2.5, "voiced": 1, "voicing_changes_per_s": 0 }, { "flatness": 0.001, "high_zcr_ratio": 0.1, "label": "speech", "level_db": -13.4, "low_energy_ratio": 0.26, "periodicity": 0.971, "pitch_grid_concentration": 0.518, "start_s": 3, "voiced": 1, "voicing_changes_per_s": 0 }, { "flatness": 0.002, "high_zcr_ratio": 0.24, "label": "speech", "level_db": -14.5, "low_energy_ratio": 0.38, "periodicity": 0.961, "pitch_grid_concentration": 0.425, "start_s": 3.5, "voiced": 1, "voicing_changes_per_s": 0 }, { "flatness": 0.002, "high_zcr_ratio": 0.26, "label": "speech", "level_db": -16.9, "low_energy_ratio": 0.58, "periodicity": 0.948, "pitch_grid_concentration": 0.071, "start_s": 4, "voiced": 1, "voicing_changes_per_s": 0 }, { "flatness": 0.002, "high_zcr_ratio": 0.22, "label": "speech", "level_db": -15.4, "low_energy_ratio": 0.44, "periodicity": 0.946, "pitch_grid_concentration": 0.114, "start_s": 4.5, "voiced": 1, "voicing_changes_per_s": 0 } ] }, "service": "speech-music-segment", "status": "success" }, "type": "json" }