Sage
 Back
Open Source · Privacy
2026 – Present

Sage

Platform
Raspberry Pi
Language
Python
Status
Actively Building
Audio to Cloud
Never
Hardware
Raspberry Pi
Language
Python
Cloud Audio
Zero storage
Source Code
Coming to GitHub

Always listening —
and always saving.

Commercial voice assistants have always sent audio to the cloud for processing — that was the known trade-off from day one. But for a while, some devices offered a middle ground: an opt-out setting that kept certain voice interactions local, never leaving the hardware. That option is gone now. In early 2025, it was quietly removed. The official reason was AI: newer generative features require more processing power than the device itself can provide, so everything goes to the cloud, without exception, and without a way to decline.

The convenience was never the problem. A voice assistant is genuinely useful for the small, repetitive things — timers, music, reminders. But those tasks don't require a server farm. They never did. The cloud dependency isn't a technical necessity for a kitchen timer. It's a data strategy. "Always-on" and "always uploading" are two different things, and they don't have to come as a package.

"Always-on shouldn't mean
always uploading."
What Changed
In early 2025, the last remaining opt-out for local voice processing was removed from major commercial smart speakers. The stated reason was generative AI — new features need the cloud. The effect was that users lost the ability to keep any part of their voice data on-device, with no alternative offered.
The Gap
No mainstream voice assistant gives you the full feature set without the cloud dependency. Sage is built to close that gap — doing the everyday things well, without sending a single byte of your voice anywhere.

The things you actually
use an assistant for.

Sage is built around the tasks that make a voice assistant genuinely useful day-to-day — not an AI chatbot, not a smart home hub. Just the practical stuff, done reliably, without the surveillance footprint.

🎵
Spotify Playback
Voice-controlled music through Spotify. Ask for an artist, playlist, or album and Sage handles it — the audio plays locally, the request stays local.
Kitchen Timers
Set timers by voice, hands-free, while cooking. Multiple timers, named or numbered, with verbal confirmation and alerts when they're up.
🔔
Verbal Reminders
Schedule reminders by voice and Sage will speak them back to you at the right time. No app required, no phone to check.
👂
Wake Word Detection
Sage listens for its wake word and only activates on command. No continuous audio stream, no recording between activations.
🔒
No Cloud Audio
Voice is processed locally on the Raspberry Pi. Audio is never sent to an external server, never stored, never uploaded. What happens in the kitchen stays in the kitchen.
🌐
Internet Where It Counts
Sage uses internet connectivity only for services that genuinely need it — like streaming music from Spotify. The voice pipeline itself stays local.

Python on a
Raspberry Pi.

Sage runs entirely on a Raspberry Pi in Python. The goal was to build something that lives in the kitchen like a small appliance — always available, never demanding, and completely understandable by anyone who wants to look at the code.

Keeping it Python-only wasn't just a language preference — it was a constraint that keeps the project readable, accessible, and easy to fork. The entire stack, from wake word detection through command parsing and response, is written in a single language.

Hardware — Raspberry Pi, running headless as a dedicated voice assistant
Language — Python only, no secondary scripts or compiled dependencies
Voice pipeline — local wake word detection, local speech processing; nothing routed through external APIs
Internet — used selectively, only for outbound service calls like Spotify that require it by nature
Status — actively in development; core features being built and tested in 2026

Built in the open,
coming soon.

The whole point of Sage is that you can see exactly what it does and doesn't do with your voice. Closed-source privacy claims are just claims. Open source is a receipt.

The project will be released publicly on GitHub once it reaches a stable, usable state. The plan is to make it easy enough to run that anyone with a Raspberry Pi and a reason to distrust their smart speaker can set it up themselves.

Coming soon to GitHub. Sage will be released as a public, open-source repository once the core feature set is stable. The code will be free to use, fork, and adapt.