IReader Logo
IReaderOpen source novel reader for Android & Desktop
Docs

Text-to-Speech Setup Guide

IReader Desktop includes integrated Text-to-Speech powered by Piper TTS, providing natural AI narration for your reading experience. This guide walks you through setting up and configuring TTS.

System Requirements

  • Platform: Windows 10+, macOS 10.15+, or Linux with ALSA/PulseAudio
  • RAM: 4GB minimum
  • Disk Space: 500MB for the app plus additional space for voice models (50-200MB per model)

Initial Setup

  1. Launch IReader Desktop and open any book in the reader view.
  2. Look for the TTS controls in the reader toolbar (speaker icon).
  3. On first use, IReader will prompt you to download a voice model.
  4. Select your preferred language and voice quality level:
    • Low Quality: Faster, smaller file size (~50MB)
    • Medium Quality: Balanced performance and quality (~100MB)
    • High Quality: Best naturalness, larger file size (~200MB)

Downloading Voice Models

  1. Navigate to Settings → Text-to-Speech → Voice Models.
  2. Browse available languages and quality levels.
  3. Click Download next to your preferred voice model.
  4. Wait for the download to complete (models are cached locally for offline use).
  5. Set your default voice in Settings → Text-to-Speech → Default Voice.

Using TTS in the Reader

  1. Open any book and navigate to the chapter you want to read.
  2. Click the speaker icon in the toolbar or press Ctrl+T (Windows/Linux) or Cmd+T (macOS).
  3. TTS will begin reading from your current position with word-level highlighting.
  4. Use the playback controls to:
    • Play/Pause: Space bar or click the play button
    • Skip Forward/Back: Arrow keys or navigation buttons
    • Adjust Speed: Use the speed slider (0.5x to 2.0x)
    • Change Voice: Select from downloaded models

Customization Options

Playback Speed

Adjust reading speed in Settings → Text-to-Speech → Playback Speed:

  • 0.5x (slow, good for learning)
  • 1.0x (normal)
  • 1.5x (faster)
  • 2.0x (very fast)

Word Highlighting

Enable or customize word highlighting in Settings → Text-to-Speech → Highlighting:

  • Toggle highlighting on/off
  • Adjust highlight color
  • Change highlight animation style

Auto-Advance

Configure automatic chapter progression in Settings → Text-to-Speech → Auto-Advance:

  • Enable/disable auto-advance to next chapter
  • Set delay between chapters (0-10 seconds)

Keyboard Shortcuts

  • Ctrl/Cmd + T: Toggle TTS on/off
  • Space: Play/Pause
  • Left/Right Arrow: Skip backward/forward by sentence
  • Up/Down Arrow: Adjust playback speed
  • Esc: Stop TTS and close controls

Managing Voice Models

Viewing Downloaded Models

  1. Go to Settings → Text-to-Speech → Voice Models.
  2. Downloaded models are marked with a checkmark.
  3. View storage space used by each model.

Deleting Models

  1. Navigate to Settings → Text-to-Speech → Voice Models.
  2. Click the trash icon next to any downloaded model.
  3. Confirm deletion to free up disk space.

Tips for Best Experience

  • Download multiple languages: If you read in multiple languages, download voice models for each.
  • Use high-quality voices: For the best listening experience, use high-quality models when storage permits.
  • Adjust speed gradually: Start at 1.0x and adjust based on your comfort level.
  • Enable word highlighting: Visual tracking helps maintain context while listening.
  • Use headphones: For better audio quality and immersion.

Next Steps