HALOWERK medienwerk

Takes an image by URL or inline base64 and returns its colour palette: up to sixteen colours, each with the share of the visible area it covers, its HEX and sRGB values, its OKLCH coordinates, and the WCAG 2.1 contrast ratio against white, against black and against every other colour in the palette.

Takes an audio or video file by URL or inline base64 and returns the transcript: the full text, every word with start and end time and its own confidence, the utterances and paragraphs the recogniser separated, and the detected language with its confidence where no language was specified. Alongside

Takes an audio or video file by URL or inline base64 and reports who spoke when. Every turn comes back with its speaker label, start and end time, duration, word count and text, and consecutive words from the same speaker are merged into one turn rather than left as a word list. On top of the turns

Takes a document as text, a public URL or inline base64 — PDF, DOCX, ODT, HTML and Markdown are read — and returns it translated into the target language. Structure is the point: heading levels, indentation, blank lines, list markers, the number of table columns, placeholders such as double-brace to

Takes a text and returns it spoken, as MP3, WAV, Opus, FLAC or raw linear16, encoded base64 with its media type and the resulting running time. The voice is chosen freely from the provider catalogue — over a hundred voices across languages and accents — and is validated against that catalogue before

Takes an image by URL or inline base64 and returns it with the background removed, as PNG or WebP with a real alpha channel, together with the share of the frame that survived, the bounding box of the remaining subject and the option to crop to it. The whole computation runs locally with rembg and t

Takes one file, by URL or inline base64, and returns it in the format you ask for. Text documents go through pandoc, so DOCX, ODT, EPUB, HTML, Markdown, RST, Org, LaTeX, RTF, MediaWiki, Textile, CSV and Jupyter notebooks convert in both directions. A PDF is a one-way street: its text is extracted wi

Takes two documents, by URL, inline base64 or raw text, extracts the text of each and compares them. Paragraphs are the unit: the answer lists every block that was removed, added, or kept but reworded, and for reworded blocks it names the individual words that went and came, so a single changed numb

Called without "fields" it inspects: every AcroForm field of the PDF comes back with its name, type, current value, whether it is required or read-only, the permitted options for dropdowns, radio groups and list boxes, and the character limit of text fields. Called with "fields" it fills exactly tho

Takes between two and eight images by URL or inline base64 and compares each pair. Three perceptual hashes are computed, because each fails differently: an average hash over an 8x8 grey image is cheap but moves with brightness, a gradient hash reads the slope between neighbouring pixels and survives

Takes one media file by URL or inline base64 and reads its C2PA manifest store. The answer says whether a manifest is present at all, whether the cryptographic checks pass — every failing check is returned with its code and explanation, so a hash mismatch on the image data is distinguishable from a

Takes a video by URL or inline base64 and reports where the picture changes. FFmpeg measures the difference between consecutive frames; every jump above the threshold starts a new scene, and the answer lists each scene with start, end, duration and the fraction of the running time it covers, plus th

Downloads one public PDF up to 5 MiB through SSRF-safe redirect checks or accepts extracted text, runs pdftotext in a private temporary directory, and deterministically extracts the requested codes with their source lines. Temporary PDF and text files are deleted before the response. It does not OCR

Uses the existing Deepgram and local media pipeline with one diarized transcription call. Subtitle cues split at speaker changes, pauses, six seconds or 84 characters. Unknown speakers remain null. Requires a lawful recording; submitted audio leaves this server for Deepgram, with the existing provid

Takes matched object and image points from multiple views of a planar calibration target and returns the camera matrix, five distortion coefficients and the RMS reprojection error that the fit actually achieved. The error figure is the point: it tells a caller whether the calibration is usable befor

Given paired calibration observations and the intrinsics of both cameras, this computes the rotation and translation between them and derives everything a stereo pipeline needs downstream: rectification transforms for both views, both projection matrices, and the disparity-to-depth mapping. The RMS

Solves for the rigid transform between an object's coordinate frame and the camera, given 3D landmark coordinates, where those landmarks appear in the image, and the camera matrix and distortion. Returns the rotation and translation together with the reprojection RMSE, so a caller can tell a well-co

Fits a 2D projective transform between two point sets with RANSAC at a caller-chosen reprojection threshold, and returns both the homography and the inlier mask. The mask is what makes this useful beyond a plain fit: bad correspondences are named rather than quietly averaged in, so a caller can re-r

Triangulates 3D positions from corresponding points in two calibrated views using the supplied projection matrices. Degenerate cases are reported honestly: a correspondence whose rays are near-parallel has no finite intersection, and it comes back as null with its position in the finite mask, instea

Runs semi-global block matching over a rectified grayscale stereo pair and returns per-pixel disparity together with the count of pixels that could actually be matched. Pixels with no reliable match stay unmatched rather than being interpolated, so occlusions and textureless regions are visible in t

Computes dense Farneback optical flow between two consecutive grayscale frames and returns the horizontal and vertical displacement of every pixel. Unlike sparse tracking this covers the whole image, which is what you want for measuring motion in regions with no distinct features to track — smoke, w

Finds the external contours in a caller-supplied binary mask and reports, for each, its area, perimeter, centroid and bounding rectangle, plus the total foreground pixel count. The division of labour is deliberate: segmentation is a domain decision, so the mask comes from you and the measurement com

Solves the hand-eye problem: given a series of gripper-to-base poses read from the robot and the matching target-to-camera poses seen by the camera, it recovers the rigid transform between camera and gripper that stays constant as the arm moves. This is what lets a robot act on what its camera sees.

Resamples a grayscale image to remove radial and tangential lens distortion, using the camera matrix and five distortion coefficients you supply — typically from a planar calibration. Dimensions and camera matrix are preserved, so the corrected image drops into an existing pipeline without any chang

Calculate recognized words per recorded minute without acoustic or fluency inference. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/

Measure union coverage of recognized word timestamps within the recording. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text proces

Allocate recognized word durations by anonymous speaker label, including unknown labels. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestam

Calculate word pace per recognized speaking interval for each anonymous label. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text pr

Produce a timestamped manual-review list for unknown speaker labels. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing o

Index gaps between recognized words without claiming acoustic silence. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing

Index subtitle display gaps for caption coverage review. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acou

Propose cuts inside two-second word gaps with safety padding; never execute. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text proc

Propose outer trim boundaries from recognized words with quarter-second padding. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text

Separate provider confidence bands from unknown confidence values. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing onl

Measure subtitle Unicode-codepoint reading speed and its distribution. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing

Flag fast, short and text-heavy cues for explicit editorial review. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing on

Summarize cue display durations and locate the shortest source cue. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing on

Measure word load and word rate per subtitle cue. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VA

Create a two-line caption layout without dropping source text and mark overflow. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text

Convert source cue ranges to outward-rounded25fps frame intervals. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing onl

Build a labeled speaker-turn edit range list without executing edits. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing

Produce path-free FFmpeg filter expressions for source-backed speaker turns. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text proc

Create escaped XML editor markers with actual speaker-turn source ranges. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text process

Export a spreadsheet-safe timestamped-word table with speaker/confidence columns. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text

Build a Unicode lowercase token-to-word-time search index without stemming. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text proce

Identify consecutive repeated recognized tokens without deleting speech. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processi

Cross-reference subtitle cues with contained source words and flag label mismatch. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/tex

Identify words not fully contained in any subtitle cue. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acous

Compute stable source cue SHA256 digests for caller-managed caption change detection. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/

Locate caller-specified literal redaction strings; no semantic PII detection. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text pro