Creative x402 offerings

AI music generation from a text prompt. Creates a complete original song with vocals, melody, and full arrangement as a finished MP3, not a loop or preview. Describe genre, mood, instrumentation, and…

AI image generation from a text prompt. Generate album and single cover art, podcast and video thumbnails, social and campaign graphics, concept art, storyboard frames, product shots, and article ill…

Generate Code128, EAN-13, UPC-A and Code39 barcodes as crisp SVGs in one POST. Ready for inventory, shipping and retail agents. Pay per call with USDC (x402) or credits - archtools.dev

Direct IIIF image URLs (multiple resolutions) for a specific page of a public-domain illustrated classic, with work context and provenance. Params: ?work=<work_id>&leaf=<n>

Browse Internet Archive's music collection (audio_music) as catalogued here: most downloaded items first, with year, creator, rights status and download links; add words to search within the collection. $0.01 per page of 20.

Browse Internet Archive's community-uploaded audio collection (opensource_audio) as catalogued here: most downloaded items first, with year, creator, rights status and download links; add words to search within the collection. $0.01 per page of 20.

Convert text to natural-sounding audio via ElevenLabs (returns base64 MP3). Pay per call with USDC (x402) or credits - archtools.dev

Transcribe audio to text in 100+ languages via Whisper. Send a file URL, get an accurate transcript back in one call. Pay per call with USDC (x402) or credits - archtools.dev

Generate images from text prompts. Pay per call with USDC (x402) or credits - archtools.dev

Convert text to natural-sounding audio via ElevenLabs (returns base64 MP3). Pay per call with USDC (x402) or credits - archtools.dev

Generate one bounded, commercial-safe 768x768 PNG concept image for a single everyday product. Async result retrieval uses a private bearer token returned after an exact $0.09 Base-USDC x402 payment.

Blends artistic filters to transform images into stylized visuals.

Convert an uploaded image into terminal-friendly ASCII art.

Adapts AI writing tone to match a specific audience.

Extract/convert the audio track of any media URL (mp4, mov, wav, m4a, ogg…) to MP3 - the "mp4 to mp3" conversion, deterministic ffmpeg, no AI. Body: {"url":"https://…/video.mp4","bitrate":"192k"?}. Returns the MP3 as base64.

Loudness-normalize any audio/video URL to a target LUFS with ffmpeg's loudnorm (EBU R128) and return MP3 - consistent levels for podcasts, clips, and TTS output. Body: {"url":"https://…/audio.wav","targetLufs":-16?}.

Search audiobook titles and metadata by query.

Speech-to-text for one immutable audio or video artifact, returning normalized text and timed segments for audio-to-text or video transcription workflows.

Text to speech (TTS) API: natural English speech with 28 voices (American and British, female and male; Kokoro-82M, open-licensed). Returns MP3 or WAV. Default voice af_heart; list voices at GET /v1/voices. Runs at about real time: 1,000 characters take about a minute. Priced per character.

Text to image generation: one image from a text prompt (FLUX-class model, up to 768 px), returned as PNG, JPEG or WebP. Runs on CPU, so it is slow. Takes about 3-5 minutes per image.

YouTube transcript API: the full transcript of a YouTube video (or another site with captions) from its own captions in seconds, as txt, srt, vtt or JSON segments with timestamps, title and language. No speech recognition, flat price per video up to 4 hours. Videos without captions are refused before payment; use /v1/transcribe for those.

a play of b702 — You can use it for the time you paid for. What it opens for you is yours, and the creator who sold it to you keeps paying to host it.

Use when an agent needs a web-ready image: shrinks a PNG, JPEG or WebP to a maximum width and converts it to WebP, keeping transparency.

Remove Background: Removes the background from one photo and returns the subject on a transparent background as a PNG, at the photo's own size.