Der Creative Claw MCP-Server,
verbunden mit einem Klick.

“Nutze „generate_image“: Generate or edit images using AI models. **Two modes:** - **Generate** (no image_url): Create an image from a text prompt. - **Edit** (with.”

“Nutze „compare_models“: Generate the same image with multiple models side-by-side for comparison. All models receive the same prompt and settings, and results are d.”

“Nutze „generate_video“: Submit a video generation job using AI models. Returns a job ID immediately — video generation runs in the background (typically 30s–2min).”

“Nutze „generate_speech“: Generate speech audio from text using AI text-to-speech models. Returns a permanent audio URL with an inline audio player. Recommended TTS.”

generate_image — Generate or edit images using AI models. **Two modes:** - **Generate** (no image_url): Create an image from a text prompt. - **Edit** (with

compare_models — Generate the same image with multiple models side-by-side for comparison. All models receive the same prompt and settings, and results are d

generate_video — Submit a video generation job using AI models. Returns a job ID immediately — video generation runs in the background (typically 30s–2min).

generate_speech — Generate speech audio from text using AI text-to-speech models. Returns a permanent audio URL with an inline audio player. Recommended TTS

transcribe — Transcribe audio or video to text using ElevenLabs Scribe (multilingual, with word-level timestamps and speaker diarization). **Caching:**

isolate_audio — Clean up an audio file using ElevenLabs Voice Isolator — removes background noise, music, and reverb so only the voice remains. **Workflow:

render_html_image — Render HTML/CSS to a PNG image via headless Chromium. Great for branded graphics (social cards, banners, OG images) — faster and cheaper tha

render_html_video — Render an HTML/CSS/JS composition to an MP4 video using HyperFrames on Modal.com. **This tool is asynchronous.** It returns immediately wit