CreativeClawCo/creative-claw-marketplace

**Generate on-brand media inside ChatGPT, Codex, Claude, Cursor, Grok Bot, Hermes, and OpenClaw.**
Creative Claw is an MCP plugin that brings a full AI media studio into Grok Bot, Hermes Agent, OpenClaw, Cursor, Claude Code, Claude Desktop, ChatGPT, and Codex. Generate images, video, and expressive speech; reuse Characters and brand assets; and produce product campaigns, UGC ads, and multi-shot Films through one account. No API keys and no platform switching.
> creativeclaw.co | Install in ChatGPT | ChatGPT guides | Pricing |
---
Use it in ChatGPT
ChatGPT has no built-in video generation since OpenAI discontinued Sora. Creative Claw adds it back as a plugin: install it from the ChatGPT plugin directory, sign in, and ask for what you need in plain language. It renders video with **Seedance 2.5, Gemini Omni, and MiniMax H3 Max**, images with **Nano Banana 2**, and voiceovers with **ElevenLabs or Cartesia**, including a clone of your own voice.
What people make with it, with real costs from our published examples:
| What | Cost | Guide |
| --- | --- | --- |
| Animate a still image into a 5-second 1080p clip | 146 credits ($1.46) | Animate an image |
| 15-second vertical product ad with 3 shots, voiceover, and captions | 461 credits ($4.61) | Product video ads |
| UGC-style ad with a talking presenter holding your product | 294 credits ($2.94) | UGC video ads |
| Four-scene short film with the same character in every scene | 569 credits ($5.69) | Multi-scene films |
| On-brand Instagram posts, Story, and an 8-second Reel | 288 credits ($2.88) | Social media content |
| Product photo set plus a product video from one image | 288 credits ($2.88) | Product photos |
| Clone your voice and narrate in 40+ languages | Clone is free; a 15-second voiceover is a few credits | Clone your voice |
| Weekly posts and a Reel from a ChatGPT dot | 256 credits ($2.56) a week | ChatGPT dots |
Short video walkthroughs of each are on YouTube.
---
What You Get
MCP Server
One connection to Creative Claw's MCP server gives the skills live model discovery plus media generation, editing, brand, asset, Character, Film, and feedback tools:
| Category | Tools |
| ----------------- | ------------------------------------------------------------------------------------------------------------------- |
| **Image** | generate_image (generate, edit, or repeat across models for comparison), load_image |
| **Video** | generate_video, check_job |
| **Speech** | generate_speech, design_voice, clone_voice, transcribe, isolate_audio |
| **Media editing** | remove_background, upscale_media, trim_video, cut_and_reframe_video, scale_video, add_subtitles, extract_frames, merge_media |
| **Models** | list_models, get_model_params, search_examples |
| **Assets** | search_assets, update_asset, delete_asset, upload_asset, import_media, get_upload_url, confirm_upload |
| **Brand themes** | get_theme, list_themes, update_theme |
| **Characters** | manage_character, list_characters |
| **Films** | create_film_project, update_film_project, get_film_project, list_film_projects, assemble_film |
| **Feedback** | submit_feedback |
| **Cost and account** | estimate_generation, manage_account; get_credits_balance where the client exposes it |
Current image, video, speech, music, and sound-effect models (Nano Banana 2, GPT Image 2.5, Seedream 5 Pro, Seedance 2.5, Gemini Omni, MiniMax H3 Max, ElevenLabs, Cartesia, and more) through one account with pay-as-you-go pricing. The live catalog comes from list_models.
Skills (Creative Workflows)
The **creativeclaw** root skill routes mixed or unclear requests, account questions, and the curated examples catalog. Sixteen focused outcome skills own image, video, voice, music, and sound-effect generation; Characters and avatars; planning, Films, product photoshoots, and UGC ads; editing existing media (cuts, reframing, captions, audio, intros and outros); long-video Reels; explicit HTML rendering; and feedback. Model guides are packaged as references inside the outcome skills that use them; there are no per-model skills.