Communitygithub.com

0xsline/openchatcut

通过 Mureka、MiniMax、Atlas Cloud 和 Sonilo 进行音乐生成。可用于器乐、歌曲、配乐、音轨/分轨生成、翻唱,或通过 `submit_music` 为成片进行视频条件配乐。

openchatcut 是什么?

该技能是一个多供应商音乐生成辅助工具,专为视频编辑和后期制作场景设计。它整合了四种主流 AI 音乐提供商(Mureka、MiniMax、Atlas Cloud 和 Sonilo),每种提供商支持不同的生成模式,如器乐、歌曲、配乐、翻唱、视频驱动配乐等。用户通过 `submit_music` 提交生成请求后,获得一个 `jobId`,然后调用 `track_progress` 等待结果保存到媒体池。之后可在时间线上进行放置、裁剪、循环、淡入淡出和闪避等操作。技能提供清晰的工作流指引:确认提供商和模式、阅读对应参考文档、提交任务、跟踪进度、最后放置/编辑。同时包含严格的规则,例如避免静默生成多个变体(以免产生额外费用),以及禁止混用不同提供商的参数模式。示例代码覆盖了所有提供商的典型用法,帮助开发者快速集成。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/0xsline/openchatcut/tree/HEAD/src/agent/skills/music

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

音乐

submit_music 返回一个生成 jobId;调用 track_progress 直到每个结果都保存到媒体池。放置、裁剪、循环、淡入淡出和闪避仍然是时间线操作。

提供商与模式

提供商模式参考文档
murekainstrumental、song、prompt-song、soundtrack、trackreferences/mureka.md
minimaxt2m、coverreferences/minimax.md
atlast2mreferences/atlas.md
sonilov2mreferences/sonilo.md

选择已命名/配置的供应商。默认使用 Mureka 器乐模式作为普通背景音乐。当需要人声或参考控制时,使用 Mureka 歌曲/prompt-song 模式;当需要图像/视频驱动的配乐时使用 Mureka soundtrack 模式,从歌曲/音频源生成分轨时使用 track 模式。使用 MiniMax 进行文本转音乐和翻盖模型。使用 Atlas Cloud 通过其异步音频 API 进行模式支持的文本转音乐。当音乐应从已完成成片(项目视频素材)而非文本描述创作时,使用 Sonilo v2m 模式。

共享工作流

  1. 确认提供商、模式以及是否需要多个付费变体。
  2. 阅读提供商参考文档,仅传递该提供商的参数。
  3. 提交一次,然后调用 track_progress({ target:"generation", action:"wait", jobIds:[jobId] })。
  4. 当 count 产生多个结果时,使用每一个返回的资源;不要假设只有旧的 result 字段存在。
  5. 仅在知道实际时长后,才在时间线上进行放置/裁剪/闪避。

示例

// Mureka 器乐(默认 count 特意设置为 1)
submit_music({ provider: "mureka", mode: "instrumental", prompt: "Warm lo-fi piano bed under narration", count: 1 });

// Mureka 带歌词歌曲
submit_music({
  provider: "mureka", mode: "song", prompt: "Bright modern pop", gender: "female", count: 2,
  lyrics: "[Verse]\nCity lights open the night\n[Chorus]\nWe build the future in real time",
});

// Mureka 提示词歌曲
submit_music({ provider: "mureka", mode: "prompt-song", prompt: "A hopeful road-trip anthem", styles: ["pop", "folk"] });

// 为项目视频或图像配乐
submit_music({ provider: "mureka", mode: "soundtrack", sourceAssetId: "videoAssetId", prompt: "Tense restrained documentary score" });

// 从 Mureka 歌曲 ID 生成分轨
submit_music({ provider: "mureka", mode: "track", songId: "song-id", trackType: "Drums", prompt: "Tight punchy acoustic drums" });

// MiniMax 器乐/人声
submit_music({ provider: "minimax", mode: "t2m", prompt: "Upbeat electronic tech intro", isInstrumental: true });
submit_music({ provider: "minimax", mode: "t2m", prompt: "Rainy night pop", lyricsOptimizer: true });

// MiniMax 从项目音频素材翻唱
submit_music({ provider: "minimax", mode: "cover", prompt: "Warm acoustic coffee-shop cover", referenceAssetId: "audioAssetId" });

// Atlas Cloud 文本转音乐
submit_music({ provider: "atlas", mode: "t2m", prompt: "Cinematic ambient score with restrained piano", isInstrumental: true });

// Sonilo 从渲染成片视频转音乐(提示词可选)
submit_music({ provider: "sonilo", mode: "v2m", sourceAssetId: "renderedCutAssetId" });
submit_music({ provider: "sonilo", mode: "v2m", sourceAssetId: "renderedCutAssetId", prompt: "Warm indie folk, no drums" });

规则

  • 仅在显式请求后生成;count 为 2–3 可能会成倍增加提供商费用,因此切勿静默添加变体。
  • Mureka stream:true 启用提供商的流式任务阶段,但 OpenChatCut 仍会等待持久的最终文件。
  • MiniMax 翻唱需要配置 music-cover* 模型,且必须恰好包含 referenceAssetId 或 coverFeatureId 其中之一;coverFeatureId 还需要歌词。
  • Atlas Cloud 仅支持 t2m 模式,不接受 MiniMax 的翻唱/优化器或 Mureka 特有的控制参数。
  • 切勿将 MiniMax 的音频设置字段混入 Mureka 的请求,也不要将 Mureka 的 ID/模式混入 MiniMax 的请求。
  • 生成的音乐不保证精确的节拍/落点时机;请在生成后自行裁剪并对齐。

Individual skills in this repo

This repo contains 11 individual skills — each has its own dedicated page.

0xsline/openchatcut

Connect an MCP-capable coding agent to OpenChatCut and edit local video projects. Use when the user asks to install, connect, or set up OpenChatCut; inspect or edit an OpenChatCut project; work with its timeline, transcript, captions, media, generation, motion graphics, audio, color, or export tools; or recover from an OpenChatCut MCP error.

0xsline/openchatcut

Use when acquiring or importing media into a OpenChatCut project asset library for video editing or creation, including local/attached videos, user-provided paths, public media URLs, web video/audio/image assets, upload fallback decisions, and deciding between import_media, download_media, or manual user action.

0xsline/openchatcut

Use when a OpenChatCut video editing or creation workflow needs export, render, download, share, final delivery, subtitle-file export, render choice, local-only asset handling, or export fallback explanation.

0xsline/openchatcut

AI image generation via Fal.ai, gpt-image-2, nano-banana, MiniMax image-01, and xAI Grok Imagine. Use when the user wants to generate or create an image / picture / still.

0xsline/openchatcut

Use when a OpenChatCut tool call fails or returns an unexpected shape.

0xsline/openchatcut

OpenChatCut product knowledge — UI layout, editor features, and how generation providers are configured. Use when the user asks about the product interface, how to use a feature, where to find something, or needs GUI guidance for something the agent cannot do directly. Also use as fallback when a task fails and the user needs to complete it manually in the UI. NOT for live project-state queries ("where are my folders?", "what's on my timeline?", "where is clip X?") — those are answered by `read_project`, not by this skill.

0xsline/openchatcut

AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use when the user wants a video effect (滤镜 / 特效), a transition (转场 / crossfade / wipe / cube / 3d), a mask (蒙版 / 遮罩 / reveal), a zoom / push-in (推近 / 推镜头), or a color grade — try the built-in effects (zoom, builtin LUTs) before generating a new shader.

0xsline/openchatcut

Use when checking whether agent edits are reflected in the OpenChatCut project and editor.

0xsline/openchatcut

AI video generation via Fal.ai, Seedance 2.0, Kling, MiniMax Hailuo, xAI Grok Imagine, and OFox. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation, multi-shot, or generatively editing / extending an existing clip.

0xsline/openchatcut

Text-to-Speech (TTS), voiceover, narration placement/sync, and custom sound effects (SFX) generator. Use when the user wants generated speech from text, wants to add/replace/align narration or voiceover for an existing video/timeline, wants to keep existing voiceover synced after visual retiming edits, needs voice audition/selection, or explicitly wants a newly generated/custom sound effect that is not available in the Sound Effects library.

0xsline/openchatcut

Use when the agent should ask the user for structured input with an in-chat form, including single-select, multi-select, text fields, style pickers, or voice audition choices.

相关技能