Tonwerk
script adherence
Each script step (with optional variants) is searched in the agent's turns with a fuzzy phrase matcher: content words (Snowball stop words removed) are matched exactly, by light German/English suffix stemming or by Levenshtein similarity ≥ 0.8, within a window of at most two consecutive segments; score = matched share of content words × (0.85 + 0.15 × word-order agreement). Steps with score ≥ min_score count as covered. Order is checked with the longest non-decreasing sequence of matched.
POST https://ton.halowerk.com/v1/script-adherenceInputs
| Field | Type | Required | Description |
|---|---|---|---|
| transcript | string, object, array | No | Transcript as WebVTT or SRT text (speakers from <v Name> voice tags or "Name:" prefixes), or JSON (text or object) with a list of segments, utterances, turns, cues or words carrying start, end, speaker and text – e.g. the output of medienwerk /v1/stt or /v1/diarize, Whisper, AssemblyAI or Deepgram. |
| segments | array | No | Alternative to transcript: segments with start/end in seconds, speaker and text. |
| time_unit | string | No | Unit of start/end in JSON transcripts; auto treats integer values with a median segment length above 60 as milliseconds. |
| script | array | Yes | Script steps in their intended order: strings or objects with text, variants, required and max_start_s. |
| agent_speakers | array | No | Speaker labels of the company side (agent, IVR). Rules that concern what the company says are then checked only in these speakers' segments. |
| min_score | number | No | Minimum match score for a covered step (default 0.75). |
| check_order | boolean | No | Report steps that appear out of script order. |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"required": [
"script"
],
"properties": {
"transcript": {
"type": [
"string",
"object",
"array"
],
"minLength": 1,
"maxLength": 3000000,
"description": "Transcript as WebVTT or SRT text (speakers from <v Name> voice tags or \"Name:\" prefixes), or JSON (text or object) with a list of segments, utterances, turns, cues or words carrying start, end, speaker and text – e.g. the output of medienwerk /v1/stt or /v1/diarize, Whisper, AssemblyAI or Deepgram."
},
"segments": {
"type": "array",
"minItems": 1,
"maxItems": 5000,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"start",
"end",
"text"
],
"properties": {
"start": {
"type": "number",
"minimum": 0,
"maximum": 86400,
"description": "Start time in seconds."
},
"end": {
"type": "number",
"minimum": 0,
"maximum": 86400,
"description": "End time in seconds."
},
"speaker": {
"type": "string",
"maxLength": 100,
"description": "Speaker label as delivered by diarisation, e.g. \"A\", \"SPEAKER_00\" or \"Agent\"."
},
"text": {
"type": "string",
"maxLength": 5000,
"description": "Text of the segment."
}
}
},
"description": "Alternative to transcript: segments with start/end in seconds, speaker and text."
},
"time_unit": {
"type": "string",
"enum": [
"auto",
"s",
"ms"
],
"default": "auto",
"description": "Unit of start/end in JSON transcripts; auto treats integer values with a median segment length above 60 as milliseconds."
},
"script": {
"type": "array",
"minItems": 1,
"maxItems": 50,
"items": {
"anyOf": [
{
"type": "string",
"minLength": 3,
"maxLength": 500
},
{
"type": "object",
"additionalProperties": false,
"required": [
"text"
],
"properties": {
"id": {
"type": "string",
"maxLength": 60
},
"text": {
"type": "string",
"minLength": 3,
"maxLength": 500,
"description": "Wording of the step as in the script."
},
"variants": {
"type": "array",
"maxItems": 10,
"items": {
"type": "string",
"minLength": 3,
"maxLength": 500
},
"description": "Accepted alternative wordings."
},
"required": {
"type": "boolean",
"default": true
},
"max_start_s": {
"type": "number",
"minimum": 0,
"maximum": 86400,
"description": "Step must start within this many seconds of the call start (needs timestamps)."
}
}
}
]
},
"description": "Script steps in their intended order: strings or objects with text, variants, required and max_start_s."
},
"agent_speakers": {
"type": "array",
"maxItems": 20,
"uniqueItems": true,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 100
},
"description": "Speaker labels of the company side (agent, IVR). Rules that concern what the company says are then checked only in these speakers' segments."
},
"min_score": {
"type": "number",
"minimum": 0.4,
"maximum": 1,
"default": 0.75,
"description": "Minimum match score for a covered step (default 0.75)."
},
"check_order": {
"type": "boolean",
"default": true,
"description": "Report steps that appear out of script order."
}
}
}Published input example
{
"transcript": "Agent: Good morning, thank you for calling Warehouse Energy, this is the billing team.\nCustomer: Hi, my bill is too high.\nAgent: Can I have your customer number please?\nAgent: Is there anything else I can help you with?",
"script": [
"Thank you for calling Warehouse Energy",
"Could I have your customer number",
"Can I help you with anything else",
"Thank you for your patience"
],
"agent_speakers": [
"Agent"
]
}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