An open-source system for building persistent worlds with multimodal AI.
-
Updated
Sep 29, 2026 - TypeScript
An open-source system for building persistent worlds with multimodal AI.
Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.
The open-source, self-hosted unified API for generative media. One webhook-native endpoint across Fal, Replicate, and more — bring your own keys, get persistent jobs and automatic provider failover for free.
Transcript timestamp-aligned speech filler word remover & cutlist generator (Descript / Cleanvoice)
First-3-second shortform video hook retention scorer (Submagic / Opus Clip)
Audio silence detector calculating video jumpcut cadences & pacing (Opus Clip / Descript)
First-3-second shortform video hook retention scorer (Submagic / Opus Clip)
High-resolution image canvas spatial grid tile slicer & seam blender (Magnific AI / Krea AI)
Audio silence detector calculating video jumpcut cadences & pacing (Opus Clip / Descript)
16:9 to 9:16 dynamic speaker tracking & smart reframing bounding box coordinator (CapCut)
High-resolution image canvas spatial grid tile slicer & seam blender (Magnific AI / Krea AI)
16:9 to 9:16 dynamic speaker tracking & smart reframing bounding box coordinator (CapCut)
Transcript timestamp-aligned speech filler word remover & cutlist generator (Descript / Cleanvoice)
660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) — one YAML file per entry, browsable by capability.
Execution control plane SDK for generative media.
Zero-setup creative media for agents. Generate & edit images, generate video & audio, create 3D, with no API key, no OAuth, durable hosted URLs, recoverable jobs, and cost receipts.
Private workspace for generative media with own key, domain, and storage.
AI PHOTO AND VIDEO GENERATOR | A localized multimedia synthesis utility designed to generate and edit high-resolution digital assets using neural models. It allows users to execute advanced text-to-image prompts, interpolate video keyframes, adjust aesthetic styles, and render complex visual outputs safely on local hardware layers.
To associate your repository with the generative-media topic, visit your repo's landing page and select "manage topics."