For Indie Game Developers
Generate variations, extend to exact lengths, export stems, automate overnight.
No credits burned. No recurring asset costs. Runs on your GPU.
120+ CLI Commands Stem Separation Commercial Use
Pre-made loops sound like every other indie game. Custom composers cost thousands. You need 30 variations of a menu theme, and that's not in any asset pack.
Your dungeon area needs exactly 2:30 of ambient music that loops cleanly. Stock tracks don't come in the length you need.
Adaptive audio needs separated layers: drums for combat, strings for exploration, bass for tension. Most AI tools give you a flat stereo file.
Your game has 15 areas, each needing 3 moods. That's 45 tracks. Manually generating one at a time in a web tool is not a pipeline, it's a bottleneck.
Click any video to watch real workflows inside Demodokos Foundry.
Describe a scene, get a full track. Vocals, instruments, production. Locally in seconds.
Split into vocals, drums, bass, guitar, piano. Layer them for adaptive audio.
Need exactly 2:30 for a level loop? Extend with seamless spectral blending.
Script batch generation: 50 tracks overnight. Shell scripts, CI pipelines, build tools.
"Dark dungeon ambient, low strings, dripping water, 140 seconds." Or let the Creative AI expand a brief concept into full metadata.
Generate up to 8 variations per run with deterministic seeds. Pick the best, or keep all for adaptive layers. Same seed = same result, always.
Extend to exact target length with spectral blending. Then split into stems: vocals, drums, bass, guitar, piano, each on its own track.
Use the CLI to batch-generate 50 tracks overnight. Export WAV/MP3/FLAC. Drop directly into Unity, Unreal, Godot, or your audio middleware.
Script entire generation pipelines. foundry generate, foundry stem-separate, foundry timeline-export. Feed it from a shell script, CI pipeline, or your own tooling.
Split any track into vocals, drums, bass, guitar, piano, and more. Layer them in your game engine for adaptive audio. No external tool needed.
Your boss fight needs exactly 3:00. Your menu loop needs 1:20. Extend any clip to the duration you need, with seamless spectral blending at boundaries.
Same seed + same prompt = identical output. Reproduce any generation. Version-control your audio pipeline like you version-control code.
A battle cue has a glitchy moment? Patch just that region. Need the same melody in a different style for a different area? Use Cover mode to restyle it.
Arrange multi-track mixes. Apply EQ, reverb, compression, pitch shifting. Export the final mix or individual tracks. Full post-production built in.
# Generate 5 variations of a forest theme
$ foundry creative-agent-process "peaceful forest, wind, birds, 90 seconds"
Creative AI composing…
$ foundry generate --variations 5 --seed 42
5 variations generated (seed 42-46)
# Extend the best one to exactly 2:30
$ foundry extend --target-length 150
Extended to 2:30, boundaries blended
# Separate into stems for adaptive audio
$ foundry stem-separate
Stems: vocals, drums, bass, guitar, piano
# Export all stems as WAV
$ foundry timeline-export forest_theme.wav --per-track
Exported 5 tracks → forest_theme/The control utility works locally or over network. Full help and examples are built in.
Every track above was created by Foundry from a simple text description. No pre-made music, no recording studio needed.
Start free, then upgrade when you're ready. All plans run entirely on your computer, no cloud processing, no waiting, no limits.
Start creating today
Full creative suite
API + Automation
All processing runs on your computer. Private, fast, no internet needed.
Cancel anytime, no further charges. Try the Free tier first to explore.
64-bit · SSD recommended
6 GB+ VRAM · Any RTX card
12 GB+ recommended · 24 GB+ for full Creative AI
Download Demodokos Foundry and start creating. 100% local. No cloud. Just you and your music.
C474B56A67CC42BF11FCB7770808CF8F6ADD9ACCD77953876EF49DFC92CF17DB
macOS coming soon · 25% off all paid plans