Skip to main content

​
Requirements

Echophrase runs on a wide range of hardware. The default model is tuned to feel fast on a mid-range gaming GPU; a smaller “Lite” variant runs on machines with no dedicated GPU at all.

​
System

Linux is in Alpha - functional but rough around the edges (CPU-only, no GPU acceleration yet) and not yet code-signed. Global hotkeys are also not yet available on Linux; use Open Mic mode instead. Windows and macOS are fully supported, code-signed builds. See Download for details.

​
GPU acceleration

Echophrase auto-detects the fastest available device on first launch — there is nothing to configure.
DirectML is the Windows default: built into the OS, works on any vendor’s GPU, no driver / Toolkit / cuDNN version matching. NVIDIA users who already run CUDA 13.0+ and cuDNN 9.19+ can opt in from Settings -> GPU Acceleration; see GPU Acceleration.

​
Supported models

Pulled directly from the desktop app’s model registry — these are the exact models that ship today.
More models on the way. Echophrase is model-agnostic, so new backends can be added without a rewrite. We’re evaluating additional multilingual voice models. Want to vote on what ships next? Join the Discord.