Turns product pages and creative briefs into video and image ads through an AI chat workflow.
Key Features: Accepts product pages as source material Uses creative briefs as input Generates and processes 3D models through Tripo, with async jobs, format conversion, retopology, and stylization.
Key Features: Text, image, and multiview-to-3D generation Asynchronous task polling Converts, translates, compresses, and extracts files through MCP using a hosted ChangeThisFile endpoint.
Key Features: URL and base64 file input More than 1,000 documented conversion routes Temporary signed download URLs Analyze video URLs and local files for transcripts, frames, OCR text, timelines, and metadata through MCP.
Key Features: Full transcript, frame, OCR, timeline, and metadata analysis Batch analysis with resumable results Scene-change and dense temporal frame extraction Generates and edits images and videos through OpenAI and Google Veo, with MCP-aware media downloads and file outputs.
Key Features: OpenAI image generation and editing OpenAI Sora video job management Google Veo video operations and downloads Accesses RunAPI model discovery, pricing, prompt search, media tasks, account balance, and LLM endpoints through MCP.
Key Features: Model catalog browsing with filters Runtime pricing and input-constraint inspection Indexes local video and audio into searchable transcripts, keyframes, OCR results, and wall-clock evidence for agent workflows.
Key Features: Local Whisper transcription Scene keyframe extraction Connects MCP clients to OpenRouter for text, vision, audio, video, model discovery, and document reranking.
Key Features: Text chat with routing, web search, caching, and reasoning Image, audio, and video analysis Image, audio, and video generation Generates and validates logos, icons, favicons, OG images, and platform asset bundles through MCP.
Key Features: Three execution modes for zero-key, external, or API workflows Brand-aware asset generation and prompt routing Platform bundle export for app and web assets Manage a self-hosted Immich library through natural-language search, album curation, duplicate detection, reports, and galleries.
Key Features: GPS and temporal album curation Perceptual-hash duplicate detection Submit, monitor, cancel, and retrieve hosted media-processing jobs, including FFmpeg, captions, compression, and image tasks.
Key Features: Local file upload through stdio Remote FFmpeg and media-processing jobs Omnimodal MCP server converting ComfyUI workflows into tools for text, image, sound, and video generation with web UI.
Key Features: Full-modal support for text, image, sound, and video generation Dual execution modes: local ComfyUI and RunningHub cloud service Zero-code workflow-to-MCP tool conversion