> ## 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.

# Settings

> Configure Echophrase to your preferences

# Settings

Open settings from the gear icon in the main window. Settings are organized into the following sections.

## Language

Choose the UI language. Currently supported: **English** and **Traditional Chinese**.

## Account

View your email, linked providers (Google, email), and current plan tier. You can enter a license key, link additional sign-in providers, or sign out.

## Voice Model

View and change the active transcription model. Shows your GPU/device info, current model name, size, and quality rating. Click **Change** to browse and download other models.

<Note>Available models depend on your tier. See the [beta page](/beta) for a comparison.</Note>

## GPU Acceleration

Echophrase auto-detects the fastest available execution provider at runtime.
The **Auto (Recommended)** option picks the best device for your hardware:
DirectML on any Windows DirectX 12 GPU, CoreML on Apple Silicon
*(in testing)*, or NPU on Copilot+ PCs. CPU is the fallback when nothing
else is available.

You can force a specific provider if you need to:

* **Auto (Recommended)**: Let Echophrase pick the fastest device at session start
* **DirectML**: Force Windows DirectML (any DirectX 12 GPU)
* **CoreML**: Force Apple Metal (macOS 13.3+ on Apple Silicon — *in testing*)
* **CPU**: Force CPU — useful for battery savings or when the GPU is busy elsewhere

<Note>CUDA support was removed; DirectML covers NVIDIA GPUs on Windows with
no driver/toolkit version juggling. See [GPU Acceleration](/config/gpu) for
the rationale.</Note>

<Note>Changing the active provider requires restarting Echophrase to take effect. The settings UI shows a "Restart to apply" banner when a change needs a relaunch.</Note>

## Transform Model

Enable an optional post-processing step that applies grammar correction to transcriptions. Uses a lightweight T5 model (\~35 MB). You can write custom transformation rules or use the default grammar correction.

## Output

Control what happens after a transcription completes.

* **Format**: Plain Text (all tiers), Markdown (authenticated), JSON with custom metadata template <sup>Pro</sup>
* **Post-record actions** (choose one or more):
  * Copy to Clipboard (default)
  * Paste at Cursor <sup>Pro</sup>
  * Save as File <sup>Pro</sup> - configure an auto-save directory

## Audio Input

Select your microphone input device and adjust the **voice threshold** (0–100%) that determines when speech is detected. Use the **Test** button to see a live audio meter.

## Recording

* **Max duration**: 5–60 seconds per recording (tier-dependent)
* **Remove filler words**: Filter out "umm", "uh", "like", etc. <sup>Pro</sup>
* **Normalize numbers to digits**: Convert "three" → "3" <sup>Pro</sup>
* **Append space to incomplete sentences**: Adds a trailing space when a transcription doesn't end with `.`, `!`, or `?`, so you can pause mid-sentence and keep dictating without manually adding a space (on by default)

## Hotkeys

Set the global hotkey for toggling recording. Default: **Ctrl+Shift+R**. Click the binding to enter capture mode, then press your desired key combination. ESC cancels.

<Note>ESC and Spacebar also work as recording toggles when the app window is focused.</Note>

## Customize

Toggle visibility of UI elements <sup>Pro</sup>:

* Hotkey changer
* Transcription preview
* Output confirmations (toast notifications)
* Copy last button
* Input (mic) selector
* Model switcher
* Transcription speed display

## Data

* **Telemetry**: Toggle anonymous crash reports and usage stats (no audio or text is ever collected)
* **Get Data**: GDPR data export (once per 30 days)
* **Delete Account**: Anonymizes your account data and signs you out
* **Legal**: Links to Terms of Service and Privacy Policy

## About

View the current app version, check for updates, and access quick links to the website, support, docs, and Discord.