Creative x402 offerings

Animate a photo of a person, or a paid generation, into a short looping GIF from a motion prompt, no account needed

Restyle a photo of a person from a text prompt: same face, any style. One 1024px PNG, no account needed

Animate a photo of a person, or a paid generation, into a short looping GIF from a motion prompt, no account needed

Restyle a photo of a person from a text prompt: same face, any style. One 1024px PNG, no account needed

Creates personalized manifestation journals with guided prompts, daily reflections, and affirmation templates using AI.

Text to speech: turn up to 2,000 characters into natural-sounding speech (MeloTTS), returned as base64 audio (WAV, 16-bit, 44.1 kHz mono). Languages: English, Spanish, French, Chinese, Japanese, Korean.

QR code for any text or link, as a ready-to-use SVG image (and a data URI), with error-correction level and size options.

QR code for any text or link, as a ready-to-use SVG image (and a data URI), with error-correction level and size options.

Converts Markdown content into a PDF document.

Translate a short-drama episode, retaining subtitle cue identity and timing. A private series key carries approved terminology into later episodes and unambiguous renderings into the reverse directio…

Translate a short-drama episode, retaining subtitle cue identity and timing. A private series key carries approved terminology into later episodes and unambiguous renderings into the reverse directio…

TTS-ready voiceover narration script for video ads, explainers, podcast ads, YouTube intros or phone greetings: clean plain-text script sized to your duration at ~150 wpm, a delivery-marked version (pauses, emphasis, breaths), timed segments, voice/tone direction, alt openings, pronunciation notes for TTS engines. Paste straight into Voicebox, ElevenLabs or any voice tool.

Shot-by-shot short-form video ad script ready to shoot and cut today in CapCut, OpenCut or any editor: scene-timed visuals, exact voiceover lines, on-screen text, alt hooks for testing, CTA, caption + hashtags, platform format spec (aspect ratio, safe zones, captions) and compliance notes for TikTok, Reels, Shorts or Meta video. For creative, UGC and growth agents.

Extracts material information from images using AI.

Inspect any audio/video URL with ffprobe: container, duration, bitrate, and per-stream codec details (sample rate/channels for audio, resolution/fps for video) as JSON. Body: {"url":"https://…/file.mp4"}.

Propose padded cue clips around caller-specified literal keywords. 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 VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.

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…

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.

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.

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 the raw detection score positions.

Propose padded cue clips around caller-specified literal keywords. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor…

Timestamped source search for return planning wording; literal vocabulary only. 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 VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.

Timestamped source search for venue planning wording; literal vocabulary only. 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 VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.

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 processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.