Skip to main content

GPU Acceleration

Echophrase uses ONNX Runtime’s automatic device selection to pick the fastest available hardware for transcription at runtime. You don’t need to configure anything — the app detects your GPU on first launch and uses it automatically.

Supported Hardware

PlatformDefault AcceleratorWhat you need
WindowsDirectMLAny DirectX 12 GPU (NVIDIA, AMD, Intel) — no install
Windows (Copilot+ PC)NPUSnapdragon X or Intel Core Ultra — auto-selected
macOS (in testing)CoreML (Metal)Apple Silicon (M1+), macOS 13.3+
Linux / WSLCPUGPU acceleration on the roadmap

Why no CUDA?

CUDA support was removed in favor of DirectML. The short version: keeping NVIDIA driver, CUDA Toolkit, and cuDNN versions in sync was a constant source of “works on my machine” support tickets. DirectML ships with Windows, runs on every modern GPU regardless of vendor, and delivers comparable performance for the speech models we run. For the rare workload where CUDA still wins, the right path is the underlying ONNX Runtime — not Echophrase.

Verifying GPU Usage

  1. Open Echophrase Settings
  2. Look at GPU Acceleration — the top line shows the active device (for example: “Active: Using DirectML (NVIDIA GeForce RTX 3080)”)
  3. Transcribe a clip and confirm the transcription is fast
If the active device says “Using CPU” but you have a DirectX 12 GPU installed, see GPU Troubleshooting.

Troubleshooting

If GPU acceleration isn’t working:
  • Update your GPU drivers to the latest from the vendor (NVIDIA / AMD / Intel)
  • Confirm your GPU supports DirectX 12 (most cards from 2015 onwards do)
  • Check GPU Troubleshooting for platform-specific help