Skip to main content

Models, voices, and speed

Open Profile & settings → OpenAI TTS to configure narration defaults.

Model​

  • tts-1 prioritizes faster generation.
  • tts-1-hd prioritizes higher quality and may take longer.

Voice​

Choose the narrator voice used for new generations. Available choices are shown in the Voice menu.

Speed​

Choose the speed sent to OpenAI when generating narration. This is different from playback speed:

  • Generation speed changes the created audio.
  • Playback speed changes how fast the reader plays existing audio.

When settings take effect​

Changes apply to future generation requests. Already generated chapters keep their existing audio.