Tonwerk
guest briefing
Uses supplied speaker-labeled turns only. Question-marked sentences from another speaker immediately followed by the target become source-linked candidates; other question sentences remain separately visible. Quotes carry exact UTF-16 offsets and a bounded next-target-turn excerpt. Groups only identical normalized wording; lexical Dice review pairs stay separate. Reuses the existing statistical episode-topic-map method on titles, target turns and paired question turns. No language model,.
POST https://ton.halowerk.com/v1/guest-briefingInputs
| Field | Type | Required | Description |
|---|---|---|---|
| target_speaker_id | string | Yes | Consistent caller-assigned target speaker label across all episodes; identity is not inferred. |
| language | string | No | ICU sentence boundary locale; statistical stop words cover German and English. |
| episodes | array | Yes |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"required": [
"target_speaker_id",
"episodes"
],
"properties": {
"target_speaker_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,32}$",
"maxLength": 32,
"description": "Consistent caller-assigned target speaker label across all episodes; identity is not inferred."
},
"language": {
"type": "string",
"enum": [
"de",
"en"
],
"default": "de",
"description": "ICU sentence boundary locale; statistical stop words cover German and English."
},
"episodes": {
"type": "array",
"minItems": 2,
"maxItems": 12,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"id",
"title",
"turns"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Za-z0-9_.-]{1,64}$",
"maxLength": 64
},
"title": {
"type": "string",
"minLength": 1,
"maxLength": 160
},
"turns": {
"type": "array",
"minItems": 1,
"maxItems": 200,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"speaker_id",
"text"
],
"properties": {
"speaker_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,32}$",
"maxLength": 32
},
"text": {
"type": "string",
"minLength": 1,
"maxLength": 4000,
"description": "Original plain text retained for verbatim quotes and UTF-16 offsets."
},
"start_seconds": {
"type": "number",
"minimum": 0,
"maximum": 86400
},
"end_seconds": {
"type": "number",
"minimum": 0,
"maximum": 86400
}
}
}
}
}
}
}
}
}Published input example
{
"target_speaker_id": "guest",
"episodes": [
{
"id": "e1",
"title": "Podcast planen",
"turns": [
{
"speaker_id": "host",
"text": "Wie planst du deinen Podcast?"
},
{
"speaker_id": "guest",
"text": "Ich plane jeden Podcast mit einer Themenliste."
}
]
},
{
"id": "e2",
"title": "Themenliste weiterentwickeln",
"turns": [
{
"speaker_id": "host",
"text": "Wie planst du deinen Podcast?"
},
{
"speaker_id": "guest",
"text": "Meine Themenliste sammelt Themen für den Podcast."
}
]
}
]
}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