Local Transcription

First-Time Setup

{#if setupState === "choose"}

Choose a transcription engine. You can change this later in Settings.

Cloud (Deepgram) ~50 MB download Fast, accurate streaming transcription via Deepgram's servers. Requires internet and a Deepgram API key. Best for most users — low resource usage, works on any hardware. Recommended

Local - CPU ~500 MB download Runs Whisper AI models locally on your CPU. No internet needed after download. Good for privacy or offline use, but slower and uses more system resources than cloud.

Local - GPU (NVIDIA CUDA) ~2 GB download Runs Whisper AI models locally using your NVIDIA GPU for fast transcription. No internet needed after download. Requires an NVIDIA GPU with CUDA support.

{:else if setupState === "downloading"}

{progressMessage}

{Math.round(progress)}%

{:else if setupState === "error"}

Download Failed

{errorMessage}

{:else if setupState === "success"}

Setup Complete

The transcription engine is ready to go.

{/if}