Open Agent Platform

Flux-1.1-Pro-Ultra is an advanced MCP image generation service that can quickly generate high-quality, creatively rich images based on text descriptions. Suitable for various scenarios such as design, marketing materials, and artistic creation, supporting multiple styles and detail control.

SearXNG is a powerful MCP metasearch engine service that can simultaneously query multiple search engines and integrate results, providing rich internet information for AI models. It supports privacy-protected search and can filter and sort search results according to needs, enabling AI to obtain real-time network information.

Remove background from an image.

Minimax's Speech-02-Turbo is an advanced Text-to-Audio (T2A) model offering high-quality voice synthesis. It is specifically designed for low-latency real-time applications, providing quick responses. It supports various built-in system voices and personal voices cloned via minimax/voice-cloning. You can freely adjust speed, volume, and pitch, and control or auto-detect emotional expression. With multilingual capabilities, it is an ideal choice for developing applications requiring real-time voice interaction.

Cross-browser. Playwright supports all modern rendering engines including Chromium, WebKit, and Firefox. Cross-platform. Test on Windows, Linux, and macOS, locally or on CI, headless or headed. Cross-language. Use the Playwright API in TypeScript, JavaScript, Python, .NET, Java. Test Mobile Web. Native mobile emulation of Google Chrome for Android and Mobile Safari. The same rendering engine works on your Desktop and in the Cloud.

SD3.5 is the latest generation MCP image generation service launched by StabilityAI, based on leading Stable Diffusion technology. Compared to previous generations, SD3.5 has significant improvements in image quality, detail representation, and creative generation, capable of producing ultra-high-quality, diverse style images, suitable for various professional scenarios such as artistic creation, design, and content production.

Dia-1.6B is a cutting-edge MCP Text-to-Speech (TTS) service developed by Nari-Labs, providing ultra-high-fidelity voice synthesis capabilities. Using a 1.6 billion parameter large voice model, Dia-1.6B can generate natural speech that is difficult to distinguish from real human voices, featuring high emotional expressiveness and subtle tone variations, suitable for professional voice acting, premium content production, and scenarios requiring extremely high-quality voice output.

Minimax's Speech-02-HD is a high-quality Text-to-Audio (T2A) model optimized for high-fidelity applications like voiceovers and audiobooks. It offers rich voice synthesis features, including emotional expression control and multilingual support. Users can choose from various built-in voices or use their own cloned voices, and can finely adjust speed, volume, pitch, and emotion to create detailed and natural-sounding speech. This makes it an ideal choice for professional audio content creation.