> ## Documentation Index
> Fetch the complete documentation index at: https://docs.echophrase.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Selection

> Choose the right transcription model for your hardware

# Model Selection

Echophrase ships with a small registry of pre-vetted models. The values below
mirror the desktop app's model registry — they are the exact models you can
pick from in Settings.

## Available Models

| Model                                | Parameters | Min VRAM            | Recommended GPU                 | Realtime speed |
| ------------------------------------ | ---------- | ------------------- | ------------------------------- | -------------- |
| **Parakeet-TDT 0.6B** *(default)*    | 0.6B       | 6 GB                | RTX 3080 or better              | 12×            |
| **Parakeet Lite**                    | 120M       | None (GPU optional) | Any modern GPU, even integrated | 2–5×           |
| **T5-Mini Grammar** *(post-process)* | Mini       | —                   | Any GPU                         | —              |

## Recommendations

* **CPU only**: Parakeet Lite
* **Modern GPU (DirectX 12)**: Parakeet-TDT 0.6B for best quality, or Lite
  if you want lower memory use
* **Older / integrated GPU**: Parakeet Lite

## Changing Models

1. Open Echophrase settings
2. Navigate to **Voice Model**
3. Click **Change** and pick a model
4. Wait for the download to complete (\~1–2 minutes)

<Note>
  Models are downloaded once and cached locally. Switching between downloaded
  models is instant.
</Note>

<Tip>
  **More models on the way.** We're evaluating additional Whisper variants and
  multilingual voice models — see the
  [Requirements](/requirements) page for the latest matrix.
</Tip>