Tonwerk
lecture slide sync
Slide text comes from the PDF text layer (pdf.js, Mozilla) or from slides; words of at least three letters are lower-cased, Snowball stop words (German and English, BSD-3-Clause) dropped and plural -s stripped. Slides and segments become TF-IDF vectors with IDF over the slides; cosine similarity scores every segment against every slide. A Viterbi pass picks a slide sequence that maximises total similarity with small costs for moving on (0.02), skipping slides (0.05 + 0.02 per skipped slide).
POST https://ton.halowerk.com/v1/lecture-slide-syncInputs
| Field | Type | Required | Description |
|---|---|---|---|
| slides_pdf_base64 | string | No | Slide deck as PDF, base64 (at most 8 MiB, 300 pages); one page = one slide. |
| slides | array | No | Alternative to the PDF: the text of each slide in order. |
| segments | array | No | Timed transcript segments {start, end, text} in seconds. |
| captions | string | No | Alternative transcript: WebVTT or SRT captions. |
| audio_base64 | string | No | Alternative transcript source: lecture audio, at most 30 s, as base64 (max 10 MiB): WAV, FLAC, MP3, AAC/M4A, Ogg Vorbis/Opus, WebM and other common formats. |
| audio_url | string | No | Instead of base64: public http(s) URL of the file (max 10 MiB). |
| language | string | No | Whisper language code (ISO 639-1 such as en, de, fr; haw for Hawaiian). Omit to detect. |
| allow_backtrack | boolean | No | Allow returning to an earlier slide. |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"properties": {
"slides_pdf_base64": {
"type": "string",
"minLength": 20,
"maxLength": 11200000,
"description": "Slide deck as PDF, base64 (at most 8 MiB, 300 pages); one page = one slide."
},
"slides": {
"type": "array",
"minItems": 1,
"maxItems": 300,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 4000
},
"description": "Alternative to the PDF: the text of each slide in order."
},
"segments": {
"type": "array",
"minItems": 1,
"maxItems": 3000,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"start",
"end",
"text"
],
"properties": {
"start": {
"type": "number",
"minimum": 0
},
"end": {
"type": "number",
"minimum": 0
},
"text": {
"type": "string",
"maxLength": 2000
}
}
},
"description": "Timed transcript segments {start, end, text} in seconds."
},
"captions": {
"type": "string",
"minLength": 10,
"maxLength": 500000,
"description": "Alternative transcript: WebVTT or SRT captions."
},
"audio_base64": {
"type": "string",
"minLength": 16,
"maxLength": 14000000,
"description": "Alternative transcript source: lecture audio, at most 30 s, as base64 (max 10 MiB): WAV, FLAC, MP3, AAC/M4A, Ogg Vorbis/Opus, WebM and other common formats."
},
"audio_url": {
"type": "string",
"format": "uri",
"maxLength": 2048,
"description": "Instead of base64: public http(s) URL of the file (max 10 MiB)."
},
"language": {
"type": "string",
"pattern": "^[a-z]{2,3}$",
"description": "Whisper language code (ISO 639-1 such as en, de, fr; haw for Hawaiian). Omit to detect."
},
"allow_backtrack": {
"type": "boolean",
"default": true,
"description": "Allow returning to an earlier slide."
}
}
}Published input example
{
"slides": [
"Photosynthesis in the chloroplast",
"Krebs cycle in the mitochondria"
],
"segments": [
{
"start": 0,
"end": 4,
"text": "Photosynthesis happens in the chloroplast."
},
{
"start": 4,
"end": 9,
"text": "The Krebs cycle runs in the mitochondria."
}
]
}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