Tonwerk
ad disclosure audio
Decodes 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 rules identify explicit episode sponsorship, paid advertisements, paid partnerships and sponsor breaks. Returns the transcript, matched phrases and ASR segment intervals. Obvious quoted or negated phrases are excluded. Unsupported languages, silence,.
POST https://ton.halowerk.com/v1/ad-disclosure-audioInputs
| Field | Type | Required | Description |
|---|---|---|---|
| audio_base64 | string | No | Complete English clip, at most 20 s and 10 MiB, base64 WAV/FLAC/MP3/Ogg/AAC/WebM. |
| audio_url | string | No | Alternatively, a public HTTP(S) audio URL; private addresses are refused. |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"properties": {
"audio_base64": {
"type": "string",
"minLength": 16,
"maxLength": 14000000,
"description": "Complete English clip, at most 20 s and 10 MiB, base64 WAV/FLAC/MP3/Ogg/AAC/WebM."
},
"audio_url": {
"type": "string",
"format": "uri",
"pattern": "^https?://",
"maxLength": 2048,
"description": "Alternatively, a public HTTP(S) audio URL; private addresses are refused."
}
},
"oneOf": [
{
"required": [
"audio_base64"
]
},
{
"required": [
"audio_url"
]
}
]
}Published input example
{
"audio_base64": "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"
}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
- Tonwerk0.005 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
- Tonwerk0.02 USDC
audio description script
POSThttps://ton.halowerk.com/v1/audio-description-scriptFinds scene cuts with the ffmpeg scdet filter (scene_threshold on a 160 px wide copy), takes speech from caption cues when captions are supplied, otherwise detects it in the audio with Silero VAD v6.2 (or an energy detector). Pauses between