Skip to content

wavespeedai/wavespeed

v1.1.0MIT

Generate and edit AI media (image, video, audio, 3D) on the WaveSpeed platform: a general skill for the wavespeed CLI and MCP tools plus per-model skills (Seedream 5 Pro, GPT Image 2.5, Nano Banana, Seedance 2.5, Kling 4.0, Wan 3.0, MiniMax H3, MiniMax Speech, Veo 3.1, face swap, upscalers, watermark removal), and the WaveSpeed MCP server.

wavespeed-minimax-h3

Generate and edit videos with the open-weights MiniMax H3 model via WaveSpeed AI. Covers text-to-video, image-to-video (first and last frame), reference-to-video (up to 9 images, 3 videos and 3 audios), video edit and video extend, with 3-15 second clips at 480p, 540p, 768p (default) or 1080p and native stereo audio. Use when the user asks for MiniMax H3, or wants an affordable video from a prompt, an animated image, a clip built from reference media, an edited video, or a continued clip.

Version
1.0
Read SKILL.md at the source

Pinned to revision 1409fa97c638, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.