APIs for AI utilities and media generation, finance and crypto, social, search and e-commerce data. Agents pay per call from one balance.
Generate video with kling using text or image
APIs for OpenAI models
Web content crawler for deep crawling and extracting text/files from websites for LLMs and AI.
AI-powered video generation. Create custom remix videos from text prompts or daily themes with profile picture integration.
Multi-purpose AI gateway (x402engine). Text-to-speech, web search, wallet PnL/balances, and hotel search. Supports Base, Solana, and MegaETH networks via x402 v2.
Audio and video transcription powered by OpenAI Whisper. Convert speech to text with high accuracy.
Detect the language of input text and translate it to any specified target language. AI-powered translation supporting numerous world languages.
Custom AI-generated images from your text prompt: product visuals, concept art, social media banners, illustrations, and more. Peero turns your brief into a polished image and delivers it through Atelier CDN. Important terms: - A clear tex
Chinese pinyin, hanzi to pinyin, Mandarin romanization, 拼音转换, Chinese phonetic, Hanyu Pinyin with tones, 普通话拼音, Chinese to Latin, Mandarin transliteration, tone marks numbers. Convert Chinese characters to Pinyin (Hanyu Pinyin) with tone marks. For AI agents handling Chinese text-to-speech, Chinese language learning apps.
Scrape specific HTML elements from any fully-rendered webpage by CSS selector, returning text, HTML, attributes, and dimensions.
Search the Channel3 product catalog by text, image, category filters, or locale to discover products and their IDs.
Translate text between 11 supported languages using a self-hosted LibreTranslate engine, paid per query in USDC on Base.
MCP endpoint exposing U.S. real estate tools for home prices, rental data, and housing market indicators via the Model Context Protocol.
Pay-per-request AI 3D model generation powered by Meshy. Text to 3D, Image to 3D, retexturing, remeshing, rigging, and animation.
Pay-per-request text-to-speech on Modal. StableVoice serves the Chatterbox family of open TTS models with bundled voices, optional custom voice references, mp3/wav output, and Stab
Property-context APIs for agents. Run a free coverage preflight, then pay per call for official-record reports, local-change briefs, policy and ordinance context, and environmental
Paid text-to-speech via x402. WAV audio in 31 languages, OpenAI-compatible, no API keys.
Sub-second generative AI inference for image, video, and audio. FLUX text-to-image, image editing, background removal.
