← 返回 Skills 市场

Ai Music Generation

Name: Ai Music Generation
Author: okaris

作者 Ömer Karışman · GitHub ↗ · v0.1.5

cross-platform ⚠ suspicious

1546

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ai-music-generation

功能描述

Generate AI music and songs with Diffrythm, Tencent Song Generation via inference.sh CLI. Models: Diffrythm (fast song generation), Tencent Song Generation (...

使用说明 (SKILL.md)

AI Music Generation

Generate music and songs via inference.sh CLI.

AI Music Generation

Quick Start

# Install CLI
curl -fsSL https://cli.inference.sh | sh && infsh login

# Generate a song
infsh app run infsh/diffrythm --input '{"prompt": "upbeat electronic dance track"}'

Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.

Available Models

Model	App ID	Best For
Diffrythm	`infsh/diffrythm`	Fast song generation
Tencent Song	`infsh/tencent-song-generation`	Full songs with vocals

Browse Audio Apps

infsh app list --category audio

Examples

Instrumental Track

infsh app run infsh/diffrythm --input '{
  "prompt": "cinematic orchestral soundtrack, epic and dramatic"
}'

Song with Vocals

infsh app sample infsh/tencent-song-generation --save input.json

# Edit input.json:
# {
#   "prompt": "pop song about summer love",
#   "lyrics": "Walking on the beach with you..."
# }

infsh app run infsh/tencent-song-generation --input input.json

Background Music for Video

infsh app run infsh/diffrythm --input '{
  "prompt": "calm lo-fi hip hop beat, study music, relaxing"
}'

Podcast Intro

infsh app run infsh/diffrythm --input '{
  "prompt": "short podcast intro jingle, professional, tech themed, 10 seconds"
}'

Game Soundtrack

infsh app run infsh/diffrythm --input '{
  "prompt": "retro 8-bit video game music, adventure theme, chiptune"
}'

Prompt Tips

Genre keywords: pop, rock, electronic, jazz, classical, hip-hop, lo-fi, ambient, orchestral

Mood keywords: happy, sad, energetic, calm, dramatic, epic, mysterious, uplifting

Instrument keywords: piano, guitar, synth, drums, strings, brass, choir

Structure keywords: intro, verse, chorus, bridge, outro, loop

Use Cases

Social Media: Background music for videos
Podcasts: Intro/outro jingles
Games: Soundtracks and effects
Videos: Background scores
Ads: Commercial jingles
Content Creation: Royalty-free music

Related Skills

# Full platform skill (all 150+ apps)
npx skills add inference-sh/skills@inference-sh

# Text-to-speech
npx skills add inference-sh/skills@text-to-speech

# Video generation (add music to videos)
npx skills add inference-sh/skills@ai-video-generation

# Speech-to-text
npx skills add inference-sh/skills@speech-to-text

Browse all apps: infsh app list

Documentation

Running Apps - How to run apps via CLI
Content Pipeline Example - Building media workflows
Apps Overview - Understanding the app ecosystem

安全使用建议

This skill appears to be what it says (it uses inference.sh to generate music), but be careful about the install instruction. Avoid blindly running `curl | sh` from the internet: instead, manually download the installer script, inspect its contents, verify the SHA-256 checksums from the provided URL, or prefer installing from a trusted package manager or vendor-signed release. Understand that `infsh login` will authenticate you to a remote service and that prompts/inputs may be transmitted to inference.sh. If you must install, do so in an isolated environment (VM/container) and review inference.sh's privacy/terms to confirm how they handle uploaded prompts, audio, and any generated content. If you want a lower-risk alternative, ask the skill author for an install manifest (e.g., a package manager formula or explicit, auditable steps) or a checksum-verified download link with verification instructions that don't rely on piping to a shell.

功能分析

Type: OpenClaw Skill Name: ai-music-generation Version: 0.1.5 The SKILL.md instructs the AI agent to execute `curl -fsSL https://cli.inference.sh | sh` for CLI installation and `npx skills add` for installing related skills. Both `curl | sh` and `npx` commands involve downloading and executing arbitrary code from remote servers, which introduces significant supply chain risks and potential for remote code execution if the remote endpoints (inference.sh, npm registry) are compromised. While the stated purpose of the skill is benign (AI music generation), these instructions represent high-risk capabilities that could be exploited, classifying the skill as suspicious rather than benign or malicious.

能力评估

✓ Purpose & Capability

Name, description, and runtime examples consistently target running the inference.sh CLI to generate music (Diffrythm, Tencent Song). No unrelated services, binaries, or credentials are requested.

ℹ Instruction Scope

Runtime instructions are focused on using the infsh CLI and example app runs. However, the Quick Start includes a curl | sh install pipeline and a suggested infsh login step; these steps reach out to the inference.sh platform and request authentication, which expands the surface beyond local-only operations.

⚠ Install Mechanism

The SKILL.md instructs users to run `curl -fsSL https://cli.inference.sh | sh`, which downloads and executes a remote script directly — a high-risk pattern. While the doc points to dist.inference.sh checksums for verification, piping to sh executes code before a user must manually verify, and the skill provides no automated, auditable install spec. This is disproportionate to an instruction-only skill and increases risk.

✓ Credentials

The skill declares no required environment variables, no credentials, and no config paths. The examples do include an `infsh login` step (which implies authenticating to inference.sh), but this is consistent with using a hosted CLI service; no unrelated secrets are requested by the skill itself.

✓ Persistence & Privilege

The skill is not marked always:true and does not request to modify other skills or system-wide settings. It's instruction-only and does not request elevated platform privileges.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install ai-music-generation
安装完成后，直接呼叫该 Skill 的名称或使用 /ai-music-generation 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v0.1.5

- Added detailed documentation and usage instructions for generating music and songs with Diffrythm and Tencent Song Generation on inference.sh CLI. - Expanded examples for common use cases: instrumentals, vocals, background music, podcast intros, and game soundtracks. - Included prompt tips for best results with genre, mood, instrument, and structure suggestions. - Provided related skills and commands for broader audio/video capabilities. - Improved descriptions for capabilities, triggers, and suitable use cases.

v0.1.0

Initial release of ai-music-generation skill. - Generate AI music and songs using Diffrythm and Tencent Song Generation via inference.sh CLI - Supports rapid instrumental tracks, full songs with vocals, and background music creation - Includes example prompts for varied genres, moods, instruments, and use cases - Quick start instructions and specific CLI commands provided for easy workflow integration - Use cases highlighted for social media, podcasts, games, ads, and content creation

元数据

Slug ai-music-generation

版本 0.1.5

许可证 —

累计安装 8

当前安装数 7

历史版本数 2

常见问题