Tonwerk
video text ocr
Samples the video at sample_fps; only samples whose 160 px grey image differs from the last OCR frame (more than 0.3 % of pixels changing by more than 24 levels) are read again, at most max_ocr_frames per call (the largest changes win). The chosen frames are re-extracted at up to 1280 px width (small videos are upscaled 2x) and read with Tesseract 5.3.4 (LSTM, sparse-text mode, Ubuntu tessdata eng/deu, Apache-2.0). Lines below min_confidence are dropped; lines that recur in consecutive OCR.
POST https://ton.halowerk.com/v1/video-text-ocrInputs
| Field | Type | Required | Description |
|---|---|---|---|
| video_base64 | string | No | The video as base64 (MP4/MOV, WebM/MKV, AVI, MPEG-TS, MPEG-PS, FLV, Ogg or animated GIF; at most 10 MiB decoded; a data: URL prefix is accepted). |
| video_url | string | No | Public http(s) URL of the the video (at most 10 MiB; private, local and reserved addresses are refused). |
| start_s | number | No | Start of the analysed range in seconds. |
| duration_s | number | No | Length of the analysed range in seconds (at most 120; default: to the end of the video). |
| sample_fps | number | No | Frames checked for changes per second (time resolution). |
| language | string | No | Tesseract language data: English, German or both. |
| min_confidence | integer | No | Minimum mean Tesseract word confidence (0–100) of a returned line. |
| max_ocr_frames | integer | No | Maximum number of frames read with OCR. |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"properties": {
"video_base64": {
"type": "string",
"minLength": 16,
"maxLength": 14000000,
"description": "The video as base64 (MP4/MOV, WebM/MKV, AVI, MPEG-TS, MPEG-PS, FLV, Ogg or animated GIF; at most 10 MiB decoded; a data: URL prefix is accepted)."
},
"video_url": {
"type": "string",
"format": "uri",
"pattern": "^https?://",
"maxLength": 2048,
"description": "Public http(s) URL of the the video (at most 10 MiB; private, local and reserved addresses are refused)."
},
"start_s": {
"type": "number",
"minimum": 0,
"maximum": 36000,
"default": 0,
"description": "Start of the analysed range in seconds."
},
"duration_s": {
"type": "number",
"exclusiveMinimum": 0,
"maximum": 120,
"description": "Length of the analysed range in seconds (at most 120; default: to the end of the video)."
},
"sample_fps": {
"type": "number",
"minimum": 0.2,
"maximum": 2,
"default": 1,
"description": "Frames checked for changes per second (time resolution)."
},
"language": {
"type": "string",
"enum": [
"eng",
"deu",
"deu+eng"
],
"default": "eng",
"description": "Tesseract language data: English, German or both."
},
"min_confidence": {
"type": "integer",
"minimum": 0,
"maximum": 95,
"default": 60,
"description": "Minimum mean Tesseract word confidence (0–100) of a returned line."
},
"max_ocr_frames": {
"type": "integer",
"minimum": 1,
"maximum": 16,
"default": 10,
"description": "Maximum number of frames read with OCR."
}
}
}Published input example
{
"video_url": "https://upload.wikimedia.org/wikipedia/commons/2/2c/Rotating_earth_%28large%29.gif",
"max_ocr_frames": 4
}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