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
Can I also use OpenClaw agents to operate it? Then I'd only need bot listeners and I could offload my entire music making and never have to think about it at all, let alone deal with the results. Wouldn't that be heavenly? But really, either this is the result of someone entering the deep maw of AI psychosis or some sort of modern performance art.
I hope a young team of dedicated coders, who studied for years at the expense of their sex life to bring this experiment to us aren't reading this, they'd be mortified, bless 'em. Last edited: Jul 3, 2026 at 10:41 PM
Wow! Nice! Apparently there is now a "daw" for the musically challenged. May as well just skip this thing altogether and just go straight for "AI" created tuneage slap your name and moniker on it and be done with it.
Speaking of Audacity... you can import, and export to Audacity format, as well as Ableton, FLStudio, Audition, Resolume. Hilarious assumption considering that I worked for Brazzers, Twistys, Babes, Digital Playgroung for 12 years, also directed for PHub VR for a short stint. If you've ever watched or seen ads of any of their content, I am likely in it. Not to mention being a pro skater for 17 years, and a 'real' musician for about 17 years until I undid it all by being infected by the AI virus about 10 years ago. Haven't been laid since. If nobody else is gonna be inclusive of horses, GANTASMO is here to help. I didn't choose to be born into poverty and not be able to afford real instruments, $500 software, or fancy music edumacation (or any obviously) so I made doo(doo) with what I was handed man, cut me some slack man. Yes you can do that if you have the programming skills or know how to use OpenClaw (which I actually have never touched, but you likely could if you had the determination) You can do anything you set your mind to buddy, you just have to believe. Regarding your second question, I will leave you with a quote from the greatest president of our generation: Abraham Simpson... "A little from column A, a little from column B." Thanks for posting this so I could help clarify this glaring gaps in our presentation, and about my sex life. Oh, one more thing Hmmm... I've never seen Spotify before, but I'll check it out and resolve this seemingly atrocious style choice. It's actually geared towards AR, but VR would be easy enough to do since I've been an XR developer for the past ~9-10 years. Even before the type of generative AI that some others seem to believe that I just discovered and am so heavily dependent on. Not like I've won Hackathons at MIT or was in the DARPA 2015 DARPA Robotics Challenge Finals without a college education. theDAW actually started as a project for the Music Hack Space Hackathon at Berklee College of Music ~1 month ago, Ableton was even one of the sponsors. As a 2 person team then and since, so I'd like to believe that we've been doing decently dev and press wise. Unfortunately AI = all bad no matter what, so Old man will yell at clouds. Apologies mods, not trying to spam, but as a small team, it is hard to dispel so many misconceptions in a reasonable amount of time. Last message until more convo actually flows (wouldn't wanna firehose the chat) All of the potentially absurd sounding claims are verifiable if you know how to use the internet (or I truly am neck deep in AI Psychosis) Last edited by a moderator: Jul 4, 2026 at 7:56 AM
