NOTEGEN.Read aloud
Configure system and model speech for text playback.
Read aloud works with Chat responses and selected editor text. It is configured separately from voice transcription.
Audio Settings
Configure text-to-speech and speech-to-text features.
Mode
| Mode | Behavior |
|---|---|
| Auto (recommended) | Prefer a system voice and fall back to the configured model |
| Local only | Use operating-system voices; text is not sent to a model provider |
| Model only | Use the configured TTS model; network access and credentials are required |
Model and speed
For model speech, add a tts model under Model Configuration and select it as the read-aloud model. Speed ranges from 0.5x to 2.0x; the default is 1.0x.
If the local voice does not support a language, install that voice in the operating system or use a compatible TTS model.