TheDAW is an all-in-one application for music creation. The generative engine renders audio from several inputs: supplied init audio, a text prompt, a painted inpaint region, and the Chimera engine that analyzes, blends, and beat-aligns several source clips into one generation. The workspace opens into a full studio for composition, arrangement, editing, and mixing, and into a live rig for DJing and VJing with deep MIDI mapping for any controller. theDAW covers the full path from an initial idea through a finished render to a live performance, and pairs with theDAW-XR on Meta Quest 3 for hands-only spatial control. theDAW also ships the first non-Mac port of Google's Magenta RealTime 2, vendored as the magenta-rt2-nvidia sidecar, which runs on Windows with WSL2 and NVIDIA, on native Linux, and on cloud GPUs. Models stay under the user's control: nothing downloads at startup, local-only mode is on by default, and a model loads at the first CREATE that needs it. https://github.com/gantasmo/theDAW
Stability AI provides Stable Audio 3 and stable-audio-tools, the diffusion model and pipeline at the core of theDAW. Magenta RealTime by Google DeepMind brings real-time music generation, running through theDAW's own NVIDIA/CUDA port, the first and only non-Mac port so far. Suno powers cloud music generation. T5Gemma by Google handles text conditioning. Demucs by Meta AI handles stem separation, and basic-pitch by Spotify handles audio-to-MIDI transcription. music21 by MIT builds MusicXML, ABC, tabs, and arrangements, alphaTab and OpenSheetMusicDisplay render tablature and scores in the browser, and MuseScore engraves PDF and SVG. MLX by Apple is the inference core the Magenta port builds on, extended here with a CUDA backend. PyTorch, FFmpeg, three.js, react-force-graph, WaveSurfer.js, React, Vite, and Tailwind CSS carry the rest, alongside the wider open-source community. AI DAW ? ! https://github.com/gantasmo/theDAW
