AI & Compute

Translate text or a document URL into any of 24 languages. Supports PDF and web page URLs. Returns translated text with source language detection. Powered by Claude. Pay 150 sats per request via Bitcoin Lightning L402.

Typeset a LaTeX/TeX math expression (MathJax, AMS packages) to PNG, SVG or PDF. TeX errors are returned and you are NOT charged.

Music generation, stem separation, vocal isolation, enhancement and mastering. Rendered by the Animica GPU-miner queue. Sold only while a miner for the requested kind is online — the catalog reports available:false and the endpoint answers 503 otherwise. Returns a job handle immediately (rendering is asynchronous); polling the returned poll_url is free. Kinds: audio, audio_stems, audio_isolate, audio_enhance, audio_master.

Generate agent-ready image assets (icons, logos, social graphics, thumbnails, banners) with…

Text-to-video, image-to-video, upscale, interpolate, subtitles, background removal and shorts. Rendered by the Animica GPU-miner queue. Sold only while a miner for the requested kind is online — the catalog reports available:false and the endpoint answers 503 otherwise. Returns a job handle immediately (rendering is asynchronous); polling the returned poll_url is free. Kinds: video_t2v, video_i2v, video_multiscene, video_upscale, video_interpolate, video_subtitles, video_bgremove, video_shorts.

PREMIUM: traduce un documento largo a cualquier idioma. input='en | <texto largo>'.

Traduce un texto a inglés natural y fluido. input=texto en cualquier idioma.

Genera 5 títulos atractivos y honestos para un contenido. input=tema o texto.

Traduce a cualquier idioma. input='en | Hola mundo' (idioma destino | texto).

Generates 384-dimensional normalized dense vector embeddings from input text using local all-MiniLM-L6-v2 transformer models for RAG indexing.

Generates descriptive, context-aware natural language captions from image URLs using ViT-GPT2 vision-language models.

Executes fast conversational text generation and instruction following via high-availability decentralized LLM nodes.

Synthesizes natural human speech from text prompts using SpeechT5 neural voice generation models with multi-speaker support.

Translates text across 100+ language pairs using embedded Xenova M2M-100 sequence-to-sequence translation models.

Edit an image from a text instruction. SFW only.

GPT Image 1.5 High - GPT Image 1.5, high quality: text to picture. Clean flat art: logos, icons and stickers. Square 1024x1024, transparent PNG or JPEG. $0.138, about 25 s.

GPT Image 1 Mini Low - GPT Image 1 Mini, low quality: text to picture. The cheapest. Quick drafts and simple pictures. Square 1024x1024, transparent PNG or JPEG. $0.003, about 15 s.

GPT Image 2 Low - GPT Image 2, low quality: text to picture. Sharp detail, faces and readable text. The all-rounder. Any shape up to 3:1, transparent PNG or JPEG. $0.008, about 20 s.

AI outline generated from text

Generate a QR code as SVG or PNG (base64 and data URI) for any text, URL, payment link, Wi-Fi or vCard, with error-correction level, scale and colors.

Detect the language of a text without AI (55 languages, statistical langdetect model) with probability and alternatives. Fast and cheap for routing messages or choosing a translation.

Detect the language of a text without AI (55 languages, statistical langdetect model) with probability and alternatives. Fast and cheap for routing messages or choosing a translation.

Generate a QR code as SVG or PNG (base64 and data URI) for any text, URL, payment link, Wi-Fi or vCard, with error-correction level, scale and colors.

GPT Image 2.5 Sunburst Medium - GPT Image 2.5 Sunburst, medium quality: text to picture. Precise: every detail lands where you ask. Any shape up to 3:1, transparent PNG or JPEG. $0.015, about 25 s.