How do I run Lyria 3.5 with Swarm?

Configure Lyria 3.5 via CLI using: swarm ctl model set --provider google --model google/lyria-3.5, or switch models interactively inside the terminal TUI with /models.

Does Swarm isolate Lyria 3.5 code edits from other agents?

Yes. Swarm provisions isolated Git worktrees for every session and subagent, preventing file race conditions and keeping your main working tree clean until verification passes.

Can Lyria 3.5 be assigned to specific subagent roles?

Yes. In ~/.swarm/config.json, you can configure Lyria 3.5 as Primary/Planner (DAG task decomposition), Coder (implementation in isolated worktrees), or Finder (read-only symbol search).

Google Gemini model

Lyria 3.5

Google Lyria 3.5 flagship full-length music generation model with text and image input and stereo audio plus lyrics output.

Provider: Google Gemini
Availability: Preview
Model ID: lyria-3.5
Snapshot: 2026-10-07

Run Lyria 3.5 in Swarm

Verified CLI workflow & multi-agent architecture

Quickstart Guide →

bash — swarm run

$swarm ctl model set --provider google --model google/lyria-3.5

# Or switch interactively inside the terminal TUI:

>/models

Subagent Role Matrix

Assign Lyria 3.5 to specialized system roles in ~/.swarm/config.json:

Primary / Planner: Orchestrates full task DAGs and multi-stage pipelines.
Coder Subagent: Generates code and unit tests inside private Git worktrees.
Finder Subagent: Performs read-only code search, symbol discovery, and mapping.

System Agent Roles →Why Swarm Architecture →

← All Google Gemini models

Public catalog snapshot. Catalog availability is not a real-time provider status or an access guarantee.

Lyria 3.5 model overview

Run Lyria 3.5 in Swarm

Subagent Role Matrix