Tonwerk
ivr prompt qa
Probes and decodes the prompt (base64 or URL, at most 10 MiB and 60 s) with ffmpeg 6.1 and checks it against a target profile: container, codec, sample rate, channels, duration and size (presets g711_ulaw, g711_alaw, pcm16_8k, pcm16_16k, amazon_connect per its documentation, or a custom target). Measures on 10 ms frames: speech segments, leading and trailing silence, active speech level (mean power of active frames re full scale, a simplified ITU-T P.56 style level, compared with the nominal.
POST https://ton.halowerk.com/v1/ivr-prompt-qaInputs
| Field | Type | Required | Description |
|---|---|---|---|
| audio_base64 | string | No | Prompt audio as base64 (at most 10 MiB, 60 s). |
| audio_url | string | No | Public URL of prompt audio. |
| target | string | No | Target profile. |
| custom_target | object | No | For target=custom (ffprobe names, e.g. container "wav", codec "pcm_mulaw"). |
| level_target_dbov | number | No | |
| level_tolerance_db | number | No | |
| max_leading_s | number | No | |
| max_trailing_s | number | No | |
| max_true_peak_dbtp | number | No | |
| expected_segments | integer | No | Expected number of spoken sections. |
| min_pause_ms | integer | No | Gap that separates sections. |
| silence_threshold_db | number | No |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"properties": {
"audio_base64": {
"type": "string",
"minLength": 16,
"maxLength": 14000000,
"description": "Prompt audio as base64 (at most 10 MiB, 60 s)."
},
"audio_url": {
"type": "string",
"format": "uri",
"maxLength": 2048,
"description": "Public URL of prompt audio."
},
"target": {
"type": "string",
"enum": [
"g711_ulaw",
"g711_alaw",
"pcm16_8k",
"pcm16_16k",
"amazon_connect",
"custom"
],
"default": "g711_ulaw",
"description": "Target profile."
},
"custom_target": {
"type": "object",
"additionalProperties": false,
"properties": {
"container": {
"type": "string",
"maxLength": 20
},
"codecs": {
"type": "array",
"maxItems": 10,
"items": {
"type": "string",
"maxLength": 30
}
},
"sample_rate": {
"type": "integer",
"minimum": 8000,
"maximum": 48000
},
"channels": {
"type": "integer",
"minimum": 1,
"maximum": 2
},
"max_duration_s": {
"type": "number",
"minimum": 1,
"maximum": 600
}
},
"description": "For target=custom (ffprobe names, e.g. container \"wav\", codec \"pcm_mulaw\")."
},
"level_target_dbov": {
"type": "number",
"minimum": -40,
"maximum": -10,
"default": -26
},
"level_tolerance_db": {
"type": "number",
"minimum": 1,
"maximum": 15,
"default": 4
},
"max_leading_s": {
"type": "number",
"minimum": 0,
"maximum": 10,
"default": 0.5
},
"max_trailing_s": {
"type": "number",
"minimum": 0,
"maximum": 10,
"default": 1
},
"max_true_peak_dbtp": {
"type": "number",
"minimum": -12,
"maximum": 0,
"default": -1
},
"expected_segments": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Expected number of spoken sections."
},
"min_pause_ms": {
"type": "integer",
"minimum": 50,
"maximum": 3000,
"default": 300,
"description": "Gap that separates sections."
},
"silence_threshold_db": {
"type": "number",
"minimum": -80,
"maximum": -20,
"default": -45
}
}
}Published input example
{
"audio_base64": "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",
"target": "g711_ulaw"
}Result & documentation
Machine-readable documentation of this hub
Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.
More endpoints in this hub
- Tonwerk0.01 USDC
accessible transcript html
POSThttps://ton.halowerk.com/v1/accessible-transcript-htmlParses SRT or WebVTT (voice tags <v Name>, "NAME:" prefixes and ">>" speaker changes) or a segments array, merges consecutive cues of the same speaker into turns (a new paragraph after a pause longer than paragraph_gap_s), and writes semant
- Tonwerk0.01 USDC
ad disclosure audio
POSThttps://ton.halowerk.com/v1/ad-disclosure-audioDecodes the complete supplied clip to mono 16 kHz using resource-limited ffmpeg, checks for speech with Silero VAD v6.2 (MIT), and transcribes locally with the pinned Whisper base ONNX model (MIT / Apache-2.0). Conservative English phrase r
- Tonwerk0.005 USDC
ad insertion markers
POSThttps://ton.halowerk.com/v1/ad-insertion-markersRuns ffmpeg 6.1 silencedetect on the episode audio (base64 or URL, at most 10 MiB) and builds mid-roll candidates from internal silences and from Podcasting 2.0 chapter boundaries (a boundary inside a silence or snapped to the nearest silen