Sonilo / Game audio

Game Music with Stems

Describe the scene or upload gameplay footage, generate a cue at the length that state needs, then split it into vocals, drums, bass, and other stems and drive intensity from your game state machine.

Start free with limited credits. Free and Creator output is for personal, non-commercial use.

  • +24.35%average lift in video engagementSonilo's internal usage data, versus picking a track from a music library, as of September 2026
  • 5.3Mcopyright-risky soundtracks replacedSonilo generations to date, as of September 2026
  • 700+brands create with Sonilo, from indie studios to global teamsaccounts with a paid plan, as of September 2026
  • Licensed catalogthe model is trained on a licensed Shutterstock catalog, not scraped audiosee /licensing

How it works

How Sonilo makes a game cue you can layer

  1. 01

    Describe the state, or upload gameplay

    For example "exploration, flooded archive, restrained frame drum, glassy texture, no lead melody". Or upload a capture of the level and let its pacing set the tempo.

  2. 02

    Set the duration and generate variations

    Set the length that state needs and generate several candidates, then pick the one that holds up when you hear it against the game rather than on its own.

  3. 03

    Split the track into stems

    Run Separate Stems on the variant you picked. It splits that track into vocals, drums, bass, and other, each the same length as the mix, so they stay aligned when played together.

  4. 04

    Layer the stems from gameplay

    Import the stems as synchronized players in your engine and mute or unmute them from the game state: the quiet layers in exploration, drums when an enemy is near, the full mix in combat.

Who this is for

Best for: adaptive layers without a composer on retainer

Most AI music tools hand back one stereo file, which leaves a game with a single fixed intensity. Sonilo splits the cue you generated into vocals, drums, bass, and other, so a state machine can add and remove layers instead of crossfading between whole tracks. Because the four stems are separations of one track, they share its tempo and length and stay in phase when played together.

Sonilo runs inside the editors game teams already use. Plugins are live on the Unity Asset Store, Godot, Epic Games Fab, the Roblox Asset Store, and the Defold Asset Store, and the same generation is available over the API.

Sonilo generates a cue of the duration you ask for; it does not currently produce gapless loop points, so a state that has to run indefinitely still needs a loop region or crossfade set in your engine. It is also not a replacement for a composer on bespoke themes, exclusivity, or live recording.

Before you publish

Licensed source. Plan-based rights.

The model is trained on a licensed Shutterstock catalog. Free and Creator output is for personal, non-commercial use. Pro, Premium, Enterprise, and eligible API users have commercial-use rights under the current Sonilo Terms.

For monetized channels, paid ads, client projects, or a shipped game, check the plan used for generation and keep the output and license records with the project.

Common questions

Game Music with Stems, answered.

What stems do I get?

Separate Stems splits a generated track into vocals, drums, bass, and other. You can preview each one and download only what you need; every stem is the same length as the mix, so they stay aligned when layered.

Does Sonilo generate seamless loops?

Not today. Sonilo generates a cue at the duration you set, and that cue has its own beginning and end. For a state that runs indefinitely, set a loop region or a short crossfade in your engine, or generate two cues in the same style and alternate them.

Can I drive intensity from gameplay?

Yes. The four stems come from one track, so they share its tempo and length. Mute or unmute them from your game state machine and they stay in phase. Godot AudioStreamPlayer nodes, Unity audio mixer snapshots, Unreal MetaSounds, and Roblox Sound objects can all switch layers this way.

Does it work with Unity, Godot, Unreal, Roblox, or Defold?

Yes. Native plugins are live for Unity, Godot, Epic Games Fab (Unreal), Roblox Studio, and Defold. Any other engine can use the exported files or the API.

Can I ship this in a commercial game?

Free and Creator output is for personal, non-commercial use. Pro, Premium, Enterprise, and eligible API users have commercial-use rights under the current Sonilo Terms. Check the plan used for the generation and the intended release before publishing.

Can I also generate sound effects for the game?

Yes. Text-to-Sound-Effects and Video-to-Sound-Effects use the same account and credits. The Godot and Roblox audio guides cover SFX variation and bus setup.