Back to all work
Conversational AI Music Studio
Describe a track, then generate, remix and split stems from one chat.
The challenge
Making music is out of reach for non-musicians, and running audio models on GPUs is expensive and fiddly to operate.
What we built
Users describe a track in plain words, then generate, edit, extend, remix and split stems from a chat-driven studio. A Next.js front end talks to a FastAPI orchestrator and a Gemini planning layer, with MusicGen, ACE-Step and Demucs served on Modal GPUs. Job progress streams over WebSockets backed by Redis and Pub/Sub.
The result
All the generation sits behind one chat interface. GPU spend stays down through MD5-keyed Firestore caching and idle-scaled containers, and each layer scales on its own.