Make Music

Generate professional-grade 48kHz music clips and full songs for free using Google's Lyria 3 models.

Install
cmdop skills install agensi-make-music

Make Music is a skill that enables an AI agent to generate audio tracks from text descriptions, using Google’s Lyria 3 models accessed through the Gemini API. It supports two model variants: lyria-3-clip-preview for short loops and background clips up to 30 seconds, and lyria-3-pro-preview for full song structures running 2 to 3 minutes. Both instrumental and vocal track types are supported.

The skill handles the API handshake, directory management, and file serialization internally, delivering a ready-to-play MP3 without requiring the developer to orchestrate those steps manually. Output files are 48kHz stereo and carry a SynthID watermark.

Developers can control generation parameters including BPM, musical key, specific instruments such as 808 drums or Rhodes piano, and mood descriptors. For structured compositions, timestamped prompts let an agent define transitions between sections like intros, verses, and choruses.

The skill uses the free tier of the Google GenAI SDK, so there are no per-track costs at that usage level. It is the right choice when an agent needs to produce actual audio files rather than symbolic representations like chord charts or lyrics. It is not suited to tasks that require only lyric writing, music notation, or audio editing of existing files, nor to workflows that cannot depend on the Gemini API and the Google GenAI SDK.

Use cases

  • Generate a 30-second background music loop for a video from a text mood description
  • Produce a full 2-3 minute instrumental track with defined verse and chorus transitions using timestamped prompts
  • Specify BPM, key, and instruments to create a consistent sound palette across multiple generated tracks
  • Automate music production in a content pipeline without manual API orchestration
  • Generate vocal tracks from text prompts for rapid demo creation

When to use it

  • An agent needs to output actual audio MP3 files, not just lyrics or notation
  • The workflow requires short background clips or full song structures from text input
  • Fine-grained control over BPM, key, instruments, and mood is needed
  • The project budget requires staying within the free tier of the Google GenAI SDK

When not to use it

  • The task only requires lyric writing, chord progressions, or music notation — no audio file is needed
  • The environment cannot access the Gemini API or the Google GenAI SDK
  • Audio editing or processing of existing audio files is required
  • The output format must be something other than MP3