ASR Model Management

View, download, and manage ASR models. Models are stored locally on your Mac and can be re-downloaded at any time.

Available Models

BackendModelSizeNotes
Qwen3-ASR0.6B~600 MBFast, lightweight. Best for Chinese + English.
Qwen3-ASR1.7B~1.7 GBHigher accuracy. Recommended for most users.
MLX WhisperSmall~500 MBApple Silicon only. Good balance of speed and accuracy.
MLX WhisperLarge Turbo~1.6 GBApple Silicon only. Fast with high accuracy.
MLX WhisperLarge v3~3 GBApple Silicon only. Highest accuracy.
WhisperTiny~75 MBVery fast, lower accuracy. Good for testing.
WhisperBase~140 MBFast with decent accuracy.
WhisperSmall~460 MBGood balance for Intel Macs.
WhisperMedium~1.5 GBHigh accuracy, slower on Intel.
WhisperLarge~3 GBHighest accuracy, requires 16 GB RAM.

Downloading Models

Click the download button next to any model in Settings → General. A progress bar shows the download status in real time. You can continue using Echosy while a model downloads. Once downloaded, switch to it from the model dropdown in the recording bar.

Deleting Models

Click the delete button next to a downloaded model to remove it and free up disk space. You can always re-download it later. The currently active model cannot be deleted — switch to a different model first.

MLX Whisper models are optimized for Apple Silicon and use the GPU for fast inference. If you have an Apple Silicon Mac (M1/M2/M3/M4), these are recommended for the best Whisper performance.

Ready to get started?

Download Echosy for free and start transcribing in minutes.

Download Echosy