> ## 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.

# Transcription

> Core transcription features and capabilities

# Transcription

Echophrase uses OpenAI's Whisper model to convert your speech to text with high accuracy.

## How It Works

Echophrase captures audio from your microphone, processes it locally using the Whisper AI model, and types the transcribed text wherever your cursor is positioned.

## Supported Languages

Whisper supports 99+ languages including:

* English, Spanish, French, German, Italian, Portuguese
* Chinese, Japanese, Korean
* Arabic, Hindi, Russian
* And many more...

## Accuracy

Transcription accuracy depends on:

* **Model size**: Larger models are more accurate but slower
* **Audio quality**: Clear audio produces better results
* **Background noise**: Quiet environments work best

See [Model Selection](/config/models) to choose the right balance for your needs.