Unleash your sound
with intelligent tools

You do — completely. You keep full copyright and authorship in everything you make with Daydream, and we expressly disclaim any ownership, license, or royalty interest in it. We take no cut and no revenue share, and there's no attribution requirement. Release it on a record, put it in a game, cut it under picture — how you use it is entirely up to you. The full terms are at daydream.live/terms.

Only your own Style, and only when you ask us to. Audio you upload for Style training is used to train that Style and nothing else — we don't train any other Style, any shared model, or any other system on it, for us or for anyone else. Your Style stays private unless you choose to publish it, and you can ask us to delete your uploads at any time. We do look at non-audio signals — file metadata, quality and usage metrics, aggregate analytics — to improve the product.

From audio you bring in. You load a source — a take, a loop, a field recording, a scrap of noise — and DreamSampler builds new material out of it, with you deciding how far each result travels from the original. There's no fixed library to dig through and nothing is pulled from someone else's record.

No. There's a demo at daydream.live/demo that runs in your browser — no install, no GPU, no account. Twist the parameters and hear it respond. To work with your own audio you'll want the plugins, at daydream.live/downloads.

Yes. DreamSampler ships as a native VST3, AU, and AAX instrument, plus a standalone app for macOS and Windows. DreamMAX is a Max for Live device for Ableton Live 12 Suite. Both integrate with your project timeline, so you can automate every parameter using standard envelope lanes, macro knobs, and MIDI hardware. Download them at daydream.live/downloads.

Yes. Map any parameter directly to physical faders, knobs, and macro lanes. Control lands at 25Hz, so the sound reshapes the exact millisecond your hand moves. MIDI mapping is supported in the web app today and is first-class in the plugins.

Yes — that's Style training. Point it at songs and sounds you own and it learns your palette, so what you make afterwards comes out in your own sound rather than a stock genre preset. Your Style loads in the plugin, the browser, and TouchDesigner. There's a walkthrough at daydream.live/learn.

Soon. A catalog of Styles licensed directly from working artists is on the way — every one opt-in, and every artist paid when their Style gets used. Today you can train and play your own. If you're an artist and want in on the founding artist program, write to hello@daydream.live.

That's where this is headed. Publishing your Style so other producers can play it — and getting paid each time it's used — is on the roadmap. Until then your Style stays private unless you choose to share it.

Not for any of our hosted products. The web app, the plugins, and the TouchDesigner operator all run on Daydream's cloud — any laptop with a modern browser or DAW will work. A GPU is only needed if you want to run the open-source engine locally, in which case an NVIDIA card with at least 8GB of VRAM works (an RTX 4090 or 5090 is the sweet spot for sub-100ms latency).

Our engine is. DEMON — the engine behind every Daydream instrument — is open source and free to run locally on your own GPU, forever. The web app and the plugins run on our hosted infrastructure and you can subscribe to a plan, but the engine underneath is fully open and developed in public.

Yes — Daydream exposes an MCP server and API for programmatic control over every parameter. Build installations, custom apps, or anything else you can wire up. Join the API waitlist at tally.so/r/ja5Rex.