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

ResourceMinimumRecommended
OSWindows 10 (22H2)Windows 11
OS (macOS)macOS 13 (Apple Silicon) — Metal in testingmacOS 14+
OS (Linux)Ubuntu 22.04 (CPU only)Ubuntu 24.04
RAM4 GB8 GB+
Disk2 GB free4 GB free
GPUNone — CPU worksDirectX 12 GPU on Windows

GPU acceleration

Echophrase auto-detects the fastest available device on first launch — there is nothing to configure.
PlatformAccelerationWhat you need
WindowsDirectMLAny DirectX 12 GPU (NVIDIA, AMD, Intel, Qualcomm)
macOSMetal (in testing)Apple Silicon, macOS 13.3+
LinuxCPUGPU acceleration on the roadmap
We dropped CUDA support to escape “requirements hell” — matching the right NVIDIA driver, the right CUDA Toolkit version, and the right cuDNN version turned every install into a multi-step yak-shave. DirectML is built into Windows, runs on every modern GPU regardless of vendor, and gives us the same wins for transcription workloads with none of the install pain. Native CPU and Apple Metal cover the rest.

Supported models

Pulled directly from the desktop app’s model registry — these are the exact models that ship today.
ModelParametersMin VRAMRecommended GPURealtime speed
Parakeet-TDT 0.6B (default)0.6B6 GBRTX 3080 or better12×
Parakeet Lite120MNone (GPU optional)Any modern GPU, even integrated2–5×
T5-Mini Grammar (post-process)MiniAny GPU
For the default Parakeet-TDT model we recommend an RTX 3080 or better. Parakeet Lite runs comfortably on integrated graphics or any older NVIDIA card — you do not need a dedicated GPU to use Echophrase.
More models on the way. We’re evaluating additional Whisper variants and multilingual voice models. Want to vote on what ships next? Join the Discord.