Music Video
Build a short music video from a song theme — N keyframes, animate each, generate matching music.
Inputs
| Name |
Type |
Required |
Default |
Description |
theme |
text |
yes |
— |
Song / video theme (e.g. "lonely robot finds a friend, hopeful"). |
scenes |
int |
no |
3 |
Number of scenes (each becomes a 5s clip). |
music_style |
text |
no |
ambient cinematic, instrumental, slow tempo, warm |
Suno-style tags for the soundtrack. |
visual_style |
text |
no |
cinematic, photoreal, soft volumetric light, 16:9 |
|
Steps
Build one the plan covering:
- Layer A (parallel) — N keyframes + 1 music track all at once.
- For each scene 1..N:
muapi image generate with a beat-specific prompt +
{{visual_style}}, model=nano-banana-pro (these feed video gen).
- One
muapi audio create (kind=music) using {{music_style}}, duration =
N × 5 + a 2s tail.
- Layer B (parallel, depends on Layer A) — animate each keyframe.
- For each scene:
muapi video from-image with image=$nX.url, model=veo3.1-image-to-video,
duration=5, prompt=scene-specific motion direction.
- Return:
- The scene keyframes (asset ids in order).
- The animation clips (asset ids in order).
- The music track asset id.
- A short summary describing the cut order.
Notes
- Keep character continuity by repeating the character description in every
scene prompt verbatim.
- Don't auto-confirm any single video call > 50 cr — those need the user's
nod (the loop will prompt automatically).
- If a scene's
muapi video from-image fails after failover, fall back to
muapi video generate (text-to-video) for that scene only.
Trigger Keywords
music video, mv, video story, song visualization
Notes for the Executing Agent
- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call
muapi CLI commands. Use muapi auth configure first if MUAPI_API_KEY is unset.
- For model IDs without a CLI alias yet, fall back to the raw endpoint via
curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}' and poll with muapi predict wait <request_id>.
- Substitute
{{input_name}} placeholders with the user's actual inputs before issuing each call.
Source: hashgraph-online/awesome-codex-plugins → plugins/SamurAIGPT/Generative-Media-Skills/library/motion/music-video/SKILL.md
1---2name: muapi-music-video3description: "Build a short music video from a song theme — N keyframes, animate each, generate matching music."4category: media-and-creative5source_repo: hashgraph-online/awesome-codex-plugins6source_path: "plugins/SamurAIGPT/Generative-Media-Skills/library/motion/music-video/SKILL.md"7source_url: https://github.com/hashgraph-online/awesome-codex-plugins/blob/HEAD/plugins/SamurAIGPT/Generative-Media-Skills/library/motion/music-video/SKILL.md8metadata:9 source: https://skillmd.com/skills/hashgraph-online/muapi-music-video10---11121314# Music Video1516**Build a short music video from a song theme — N keyframes, animate each, generate matching music.**1718## Inputs1920| Name | Type | Required | Default | Description |21|:---|:---|:---|:---|:---|22| `theme` | text | yes | — | Song / video theme (e.g. "lonely robot finds a friend, hopeful"). |23| `scenes` | int | no | 3 | Number of scenes (each becomes a 5s clip). |24| `music_style` | text | no | ambient cinematic, instrumental, slow tempo, warm | Suno-style tags for the soundtrack. |25| `visual_style` | text | no | cinematic, photoreal, soft volumetric light, 16:9 | |262728## Steps2930Build one the plan covering:31321. **Layer A (parallel)** — N keyframes + 1 music track all at once.33 - For each scene 1..N: `muapi image generate` with a beat-specific prompt +34 `{{visual_style}}`, model=nano-banana-pro (these feed video gen).35 - One `muapi audio create` (kind=music) using `{{music_style}}`, duration =36 N × 5 + a 2s tail.372. **Layer B (parallel, depends on Layer A)** — animate each keyframe.38 - For each scene: `muapi video from-image` with `image=$nX.url`, model=veo3.1-image-to-video,39 duration=5, prompt=scene-specific motion direction.403. Return:41 - The scene keyframes (asset ids in order).42 - The animation clips (asset ids in order).43 - The music track asset id.44 - A short summary describing the cut order.4546## Notes47- Keep character continuity by repeating the character description in every48 scene prompt verbatim.49- Don't auto-confirm any single video call > 50 cr — those need the user's50 nod (the loop will prompt automatically).51- If a scene's `muapi video from-image` fails after failover, fall back to52 `muapi video generate` (text-to-video) for that scene only.5354## Trigger Keywords5556`music video`, `mv`, `video story`, `song visualization`575859---6061## Notes for the Executing Agent6263- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset.64- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`.65- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.6667---6869**Source:** [`hashgraph-online/awesome-codex-plugins`](https://github.com/hashgraph-online/awesome-codex-plugins) → `plugins/SamurAIGPT/Generative-Media-Skills/library/motion/music-video/SKILL.md`