Rf x402 REST usage
Call before a SEPA transfer uses a structured creditor reference. Checks ISO 11649. Does not say the invoice exists.
Image, audio, video and speech generation or processing, including transcription and voice. Priced per call or per minute where a price is published at all.
Call before a SEPA transfer uses a structured creditor reference. Checks ISO 11649. Does not say the invoice exists.
Call before an invoice to a German artist uses the Künstlersozialabgabe. Returns the 2026 percent. Not a ruling that the levy is owed.
Check whether an image can be printed at a paper size (ISO A/B, US, photo or custom mm): effective ppi, required pixels, crop or margin, colour space and ICC profile, transparency, bit depth, and a ready flag. Reads the...
Transcribe text to Unicode braille (grade-1 / uncontracted English braille), with capital and number signs. Characters with no grade-1 representation are clean 400s.
Transcribes audio to text with whisper-large-v3. Server-side fetches the audio URL (max 25 MB), relays it to Venice's audio/transcriptions endpoint, and returns the transcript…
Outbound leak check for AI agent output before it is rendered or sent: zero-click markdown-image exfiltration, data smuggled in URLs/subdomains, invisible Unicode smuggling, system-prompt and canary leaks, secrets and PI...
Use when your agent needs the gist of a long text without reading it all. Send any text (article, thread, docs, transcript); returns JSON with a one-sentence TL;DR, up to 3 key points, keywords and the language. Saves co...
Takes episodes inline or from an RSS feed whose items link transcripts via podcast:transcript (up to four transcripts are fetched, preferring VTT, JSON, SRT, HTML). Parses WebVTT voice spans, SRT cards with "Name:" speak...
Generate images, priced per image and size
Generate images, priced per image and size
Docker Hub image/repo metadata (keyless). POST {name|image|namespace+repository}. Unpaid empty → 402; after settle empty/invalid → 400 charged:false. Soft disclose package-registry / foojay / crates / nuget / deps-dev /...
Turns transcribed IVR announcements into a menu tree: keys (DTMF digits, star, hash) with option labels, actions (repeat, back, agent), voice options, sub-menus by path, unreached options and inconsistencies.
Aligns a lecture transcript with its slide deck: each transcript segment gets the slide being talked about, each slide its time range, plus slides never discussed. Takes a slide PDF or slide texts and timed segments, Web...
Recurring themes across up to 50 call transcripts: terms and two-word phrases that come up in several calls, grouped into themes with call counts, share, call ids and an example excerpt per theme. Tokenises every call (S...
Overlapping speech and interruptions per speaker from a diarised transcript or a two-channel call recording: who interrupts whom, backchannels, overlap seconds and share, with times and excerpts. Merges each speaker's se...
Escalation points in a call from keywords (legal threat, cancellation, supervisor request, complaint, repeated frustration, profanity), faster speech and, with audio, louder speech than the speaker's own median; moments...
Read an available transcript for a public Facebook video or Reel by URL.
Browse a Facebook Page's public Reels by URL, with captions, publication times and reported view badges.
Read dimension texts from a technical drawing image: lengths, diameters (Ø), radii (R), metric threads (M10x1.5), angles, ISO 286 fits (H7) and ± or +/− tolerances, with positions and the drawing scale. Tesseract 5.3.4 (...
Count people, vehicles, animals or any of 80 object classes in a photo, optionally only inside a polygon area; overlapping tiles find small objects in crowds and car parks. No identification, no crops. RT-DETRv2-S (Apach...
Read temperatures from a radiometric thermal image: FLIR radiometric JPEG (FFF raw data with Planck constants) or a 16-bit linear thermal TIFF/PNG. Min, max, mean, hot and cold spot, point and box temperatures. FLIR radi...
Supertonic TTS — long-form (≤5000 chars), auto-chunked with natural pauses.
Return a voice message as text, questions and explicitly requested actions. Only audio_url is required. Duration is measured locally and capped at20seconds before Deepgram EU processing; training opt-out sent on every re...
Return short key phrases grounded in exact transcript excerpts. Only audio_url is required. Duration is measured locally and capped at20seconds before Deepgram EU processing; training opt-out sent on every request. Trans...