Tonwerk
voice agent eval
Takes the turns of a voice-agent conversation (speaker, text, optional start/end times) and your goal criteria (required phrases per speaker, success and failure phrases). Without any language model it detects, with German and English phrase lists: agent fallback/no-match prompts, user requests for a human, agent transfers, user corrections, repeated user utterances and repeated agent prompts (normalised Levenshtein similarity >= 0.8 / 0.9), and with timestamps: response latency after each.
POST https://ton.halowerk.com/v1/voice-agent-evalInputs
| Field | Type | Required | Description |
|---|---|---|---|
| turns | array | Yes | |
| goal | object | No | |
| ended_by | string | No | |
| max_latency_s | number | No |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"required": [
"turns"
],
"properties": {
"turns": {
"type": "array",
"minItems": 1,
"maxItems": 500,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"speaker",
"text"
],
"properties": {
"speaker": {
"type": "string",
"enum": [
"agent",
"user",
"system"
]
},
"text": {
"type": "string",
"maxLength": 5000
},
"start_s": {
"type": "number",
"minimum": 0
},
"end_s": {
"type": "number",
"minimum": 0
}
}
}
},
"goal": {
"type": "object",
"additionalProperties": false,
"properties": {
"required": {
"type": "array",
"maxItems": 30,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"name",
"any_of"
],
"properties": {
"name": {
"type": "string",
"maxLength": 100
},
"any_of": {
"type": "array",
"minItems": 1,
"maxItems": 20,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 200
}
},
"speaker": {
"type": "string",
"enum": [
"agent",
"user",
"any"
],
"default": "any"
}
}
}
},
"success_phrases": {
"type": "array",
"maxItems": 30,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 200
}
},
"failure_phrases": {
"type": "array",
"maxItems": 30,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 200
}
}
}
},
"ended_by": {
"type": "string",
"enum": [
"agent",
"user",
"system",
"timeout",
"unknown"
],
"default": "unknown"
},
"max_latency_s": {
"type": "number",
"minimum": 0.2,
"maximum": 10,
"default": 2
}
}
}Published input example
{
"turns": [
{
"speaker": "agent",
"text": "Guten Tag, wie kann ich helfen?"
},
{
"speaker": "user",
"text": "Ich möchte einen Termin am Freitag."
},
{
"speaker": "agent",
"text": "Ihr Termin am Freitag um 10 Uhr ist gebucht."
}
],
"goal": {
"success_phrases": [
"ist gebucht"
]
},
"ended_by": "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