muapi-music-video
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseMusic Video
音乐视频
Build a short music video from a song theme — N keyframes, animate each, generate matching music.
Estimated credits: ~200 per run.
基于歌曲主题制作一段短音乐视频——生成N个关键帧,为每个关键帧添加动画,并生成匹配的音乐。
预计消耗积分: 每次运行约200积分。
Inputs
输入参数
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| text | yes | — | Song / video theme (e.g. "lonely robot finds a friend, hopeful"). |
| int | no | 3 | Number of scenes (each becomes a 5s clip). |
| text | no | ambient cinematic, instrumental, slow tempo, warm | Suno-style tags for the soundtrack. |
| text | no | cinematic, photoreal, soft volumetric light, 16:9 |
| 名称 | 类型 | 是否必填 | 默认值 | 描述 |
|---|---|---|---|---|
| 文本 | 是 | — | 歌曲/视频主题(例如:"孤独的机器人找到朋友,充满希望")。 |
| 整数 | 否 | 3 | 场景数量(每个场景对应一段5秒的片段)。 |
| 文本 | 否 | ambient cinematic, instrumental, slow tempo, warm | 用于音轨的Suno风格标签。 |
| 文本 | 否 | cinematic, photoreal, soft volumetric light, 16:9 | 视觉风格描述 |
Steps
执行步骤
Build one the plan covering:
- Layer A (parallel) — N keyframes + 1 music track all at once.
- For each scene 1..N: with a beat-specific prompt +
muapi image generate, model=nano-banana-pro (these feed video gen).{{visual_style}} - One (kind=music) using
muapi audio create, duration = N × 5 + a 2s tail.{{music_style}}
- For each scene 1..N:
- Layer B (parallel, depends on Layer A) — animate each keyframe.
- For each scene: with
muapi video from-image, model=veo3.1-image-to-video, duration=5, prompt=scene-specific motion direction.image=$nX.url
- For each scene:
- Return:
- The scene keyframes (asset ids in order).
- The animation clips (asset ids in order).
- The music track asset id.
- A short summary describing the cut order.
按照以下计划执行:
- A层(并行执行) — 同时生成N个关键帧 + 1首音轨。
- 针对每个场景1..N:使用带有节拍特定提示 + 的
{{visual_style}}命令,模型为nano-banana-pro(生成的结果将用于视频生成)。muapi image generate - 执行一次(类型为music),使用
muapi audio create参数,时长为N × 5 + 2秒结尾。{{music_style}}
- 针对每个场景1..N:使用带有节拍特定提示 +
- B层(并行执行,依赖A层结果) — 为每个关键帧添加动画。
- 针对每个场景:使用命令,参数为
muapi video from-image,模型为veo3.1-image-to-video,时长5秒,提示语为场景特定的运动方向。image=$nX.url
- 针对每个场景:使用
- 返回内容:
- 按顺序排列的场景关键帧资产ID。
- 按顺序排列的动画片段资产ID。
- 音轨资产ID。
- 描述剪辑顺序的简短说明。
Notes
注意事项
- 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 fails after failover, fall back to
muapi video from-image(text-to-video) for that scene only.muapi video generate
- 在每个场景的提示语中逐字重复角色描述,以保持角色连续性。
- 单个视频调用消耗积分超过50时,请勿自动确认,需等待用户确认(循环会自动提示用户)。
- 如果某个场景的命令在重试后仍失败,仅针对该场景 fallback 到
muapi video from-image(文本转视频)命令。muapi video generate
Trigger Keywords
触发关键词
music videomvvideo storysong visualizationmusic videomvvideo storysong visualizationNotes for the Executing Agent
执行Agent注意事项
- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call CLI commands. Use
muapifirst ifmuapi auth configureis unset.MUAPI_API_KEY - For model IDs without a CLI alias yet, fall back to the raw endpoint via and poll with
curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'.muapi predict wait <request_id> - Substitute placeholders with the user's actual inputs before issuing each call.
{{input_name}}
- 此流程由LLM编排:阅读每个阶段,向用户收集缺失的输入,然后调用CLI命令。如果
muapi未设置,请先执行MUAPI_API_KEY。muapi auth configure - 对于尚未有CLI别名的模型ID,通过调用原始端点,并使用
curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'进行轮询。muapi predict wait <request_id> - 在发出每个调用前,将占位符替换为用户的实际输入。
{{input_name}}