Local Models

The local engine runs Whisper on your own machine through whisper.cpp: no API key, nothing uploaded, and it works offline once the model file is downloaded.

Managing models

Open Settings → Transcription and select the Local Model (On-Device) engine. The Available Models list has All / English / Multilingual filter tabs. Each row has a Download button, a radio button that makes the model active once downloaded, and a trash icon ("Delete model") to free the disk space. Model files are fetched from the whisper.cpp repository on Hugging Face.

Available models

English-only

• Medium (English) — medium.en, 1464 MB

Multilingual (99 languages)

• Medium (Multilingual) — medium, 1464 MB
• Large V3 (Multilingual) — large-v3, 2953 MB
• Large V3 Turbo (Multilingual) — large-v3-turbo, 1617 MB

Quantized

• Large V3 Turbo Q5 (Quantized) — large-v3-turbo-q5_0, 574 MB
• Large V3 Turbo Q8 (Quantized) — large-v3-turbo-q8_0, 874 MB — the model a fresh install starts with

There is no large-v3-turbo-en: the large and turbo models exist in multilingual form only.

GPU acceleration

GPU acceleration means Metal, on Apple Silicon, and nowhere else. Speakly enables it when the platform is macOS on arm64. On Intel Macs, Windows and Linux, local transcription runs on the CPU — there is no Vulkan and no CUDA build.

• Apple Silicon (M1 and newer): the panel reads "Apple Metal detected! Local transcription will be 3x faster on your device." next to an Enable checkbox, on by default
• Everything else: the panel reads "CPU-only mode. Consider using API for faster transcription." and no toggle is shown