Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Suno Style Songsmith

    1

    Produce full songs from lyrics and style tags using the open-source HeartMuLa model stack. Use when a user wants an AI-generated track, a Suno-style demo, or lo

    Free

    5 usesSecurity scanned
    Suno Style Songsmith

    Suno Style Songsmith

    Example session with this skill installed

    Generate a 30-second acoustic folk song about a traveler returning home. Use a female vocal and 90bpm. Lyrics include [verse] and [chorus] sections.

    • Read your context and instructions
    • Compiled the suno style songsmith

    Generation complete using seed 4029. Track rendered to outputs/folk_traveler.wav.
    Style: folk, acoustic, female vocal, 90bpm.
    Model: HeartMuLa-Base.
    Note: Model license requires attribution for non-commercial use.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Generating high-quality music demos usually requires expensive cloud subscriptions or complex DAW setups. Cloud-based AI music services often lack the fine-grained control and privacy needed for local development and rapid iteration.

    What it does

    • Converts raw lyrics and style tags into full-length audio tracks locally.
    • Orchestrates the HeartMuLa model stack, including language models and audio codecs.
    • Optimizes VRAM usage through lazy loading to support GPUs with as little as 8GB.
    • Automates environment patching for RoPE caches and transformer incompatibilities.
    • Supports multi-GPU setups by splitting model and codec processing across devices.

    Frameworks & tools

    Python 3.10, HeartMuLa, NVIDIA CUDA, Transformers, and Datasets. Uses uv for dependency management and nvidia-smi for resource monitoring.

    Why this beats prompting it yourself

    Manually configuring the HeartMuLa stack is error-prone due to specific dependency versioning and hardware requirements. This skill handles the technical setup, applies necessary code patches for modern library compatibility, and manages the iterative generation workflow for you.

    Use cases

    • Generate scratch vocals and instrumental demos for songwriting sessions.
    • Create unique background tracks for video content or podcasts without cloud fees.
    • Prototype musical ideas across different genres like metal, k-pop, or lo-fi.
    • Produce localized audio assets in environments without reliable internet access.

    Known limitations

    Requires an NVIDIA GPU with at least 8GB VRAM; CPU-only generation is not supported. Performance is limited to the underlying HeartMuLa model capabilities and requires local Python environment setup.

    Requires an NVIDIA GPU with minimum 8GB VRAM. Not suitable for CPU-only systems. Requires local Python 3.10 environment.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    5 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Terminal / Shell
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    Suno Style Songsmith automates the deployment and orchestration of the HeartMuLa model stack, allowing you to generate full-length audio tracks locally from lyrics and style tags without expensive cloud subscriptions. It handles complex environment patching and VRAM optimization that would otherwise require manual technical configuration.

    This skill requires an NVIDIA GPU with at least 8GB of VRAM and a local Python 3.10 environment. It is optimized for use with AI agents capable of executing Python scripts and managing local file systems, such as AutoGPT or custom local agents.

    You receive the complete skill configuration, dependency manifests managed via 'uv', and the automation scripts needed to patch and run the HeartMuLa models. It also includes the logic for multi-GPU distribution and VRAM management to ensure smooth operation on consumer hardware.

    Yes, the skill is designed with multi-GPU support, allowing you to split the processing of the language models and audio codecs across different devices. This is particularly useful for users with multiple mid-range GPUs who want to improve generation speed or handle larger workloads.

    The skill is built to work with the open-source HeartMuLa stack; while it doesn't require a constant internet connection for generation, you will need access initially to download the necessary model weights and dependencies. Once the environment is staged, it is ideal for offline or localized audio production.