A comprehensive AI audio generation skill that creates high-quality songs, instrumentals, and podcasts through the EachLabs Predictions API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install eachlabs-music
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install eachlabs-music using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is EachLabs Music?
EachLabs Music is a specialized tool within the Openclaw Skills ecosystem designed for advanced audio synthesis and manipulation. By leveraging the Mureka and Minimax AI models, this skill allows developers to programmatically generate full musical tracks, write lyrical content, and even produce multi-speaker podcasts from simple text prompts. The skill is built to handle the entire lifecycle of audio production, from initial generation to post-production tasks like stem separation and song recognition. Integrating this into your agentic workflows via Openclaw Skills provides a robust interface for high-fidelity audio creation without needing deep expertise in digital signal processing or music theory.
EachLabs Music Use Cases
- Creating custom background music and instrumentals for digital content and gaming.
- Automating the generation of song lyrics and extending existing musical compositions.
- Producing multi-speaker podcasts and speech audio for automated media channels.
- Separating audio tracks into individual stems for remixing and production.
- Analyzing and describing existing audio files to generate metadata for large music libraries.
How EachLabs Music Works
- The system first validates the requested model capability by querying the EachLabs API with a specific slug to retrieve the required input schema.
- A prediction request is dispatched to the API endpoint containing the model version, user prompts, and configuration parameters such as duration or speaker profiles.
- The skill monitors the task status by polling the prediction ID until a terminal success or failure state is reached.
- Upon successful completion, the final output—whether it be an audio URL, text-based lyrics, or audio metadata—is extracted and returned to the agent.
EachLabs Music Setup
To enable this skill, you must provide an API key from eachlabs.ai. Configure your environment by setting the following variable:
export EACHLABS_API_KEY='your_api_key_here'
Ensure that your network environment allows traffic to api.eachlabs.ai for schema validation and prediction requests.
EachLabs Music Data Schema & Taxonomy
The skill utilizes a structured request-response pattern to manage audio tasks. Below is the primary metadata and parameter taxonomy used within this Openclaw Skills integration:
| Object | Key Parameters | Description |
|---|---|---|
| Model Validation | slug, request_schema |
Validates model existence and input requirements |
| Generation Input | prompt, duration, speakers |
Defines the creative constraints for the AI |
| File Management | upload_audio_id, purpose |
Handles source audio for extensions and stem separation |
| Prediction State | id, status, output |
Tracks the lifecycle of the asynchronous audio generation |
EachLabs Music Advanced Features
- Support for both Mureka and Minimax v2 high-fidelity music generation models.
- Seamless file upload integration for performing operations on existing audio assets.
- Advanced stem separation capabilities to isolate vocals, drums, and instruments.
- Multi-speaker podcast creation with specific voice assignments like Luna and Jake.
- Intelligent song extension that allows the AI to continue a track based on an uploaded audio reference.
SKILL.md
Loading
Related Openclaw Skills
EachLabs Image Generation
A versatile image generation skill that connects to 60+ AI models through EachLabs to turn text prompts into professional-grade images.
EachLabs Image Edit
A comprehensive image manipulation suite providing access to over 130 AI models for editing, upscaling, 3D generation, and analysis.
EachLabs Fashion AI
A professional-grade AI suite for generating fashion model photography, virtual try-on experiences, and cinematic catwalk videos.
EachLabs Face Swap
A sophisticated AI integration for swapping faces in images and videos via the EachLabs Predictions API.
EachLabs Product Visuals
Generate studio-quality product shots, lifestyle scenes, and 360-degree videos for e-commerce using specialized AI models.
EachLabs Video Edit
A comprehensive video editing suite that leverages over 25 advanced AI models to transform, upscale, and synchronize video content programmatically.
Featured*
