motu-skills

Generate speech through the motu.art Fish Audio S2 workflow API — narration, dubbing, and ad reads with inline emotion tags, voice cloning from a short reference clip, and two-speaker dialogue synthesis.

1 skill

Generate music through the motu.art Yue 2 workflow API — instrumental tracks and full songs with vocals from a structured style brief plus optional lyrics, and style covers that re-render a reference track in a new genre, arrangement, or vocal.

1 skill

AI portrait color grading and skin segmentation via the MotuArt Color Engine API. Grade portraits with a film/commercial look, or export a skin mask.

1 skill

Generate videos through the motu.art MiniMax Hailuo H3 workflow API — text-to-video, multimodal reference video (animate an image, start/end frames, talking-head lip-sync, up to 2 images + 2 audio tracks), and control-video motion transfer with structured shot-by-shot prompting.

1 skill

Generate images through the motu.art Qwen Image 2.1 workflow API — strongest on-image Chinese and English text rendering, native 512-2048 canvases, intent-matched prose prompt templates, and multi-image series with character consistency.

1 skill

Remove watermarks, logos, timestamps, and text overlays from images through the motu.art workflow API — inpaints marked regions and returns a clean image.

1 skill

Generate high-quality 2K images through the motu.art Z-Image Turbo workflow API — intent-matched prompt templates, per-image prompt design and verification, multi-image series with character consistency.

1 skill

Generate images through the motu.art Ideogram 4 workflow API — photos, illustrations, logos, posters, and images with readable rendered text.