Text to Speech
Generate speech using built-in model voices without needing a reference audio sample.
The TTS tab lets you generate speech using built-in voices that come with each model. Unlike Clone (which needs a reference audio) or Design (which needs a description), TTS gives you ready-to-use voices out of the box.
Selecting a Speaker
The left panel shows a Speaker dropdown with the built-in voices for the currently selected model. Each model has its own set of speakers. The available speakers change when you switch models.
Use Cases
Quick generation without setup
When you need speech generated fast and don't need a specific voice. Pick a built-in speaker and start generating immediately.
Comparing models
Switch between models and speakers to hear how different engines handle the same text before deciding which to use for a project.
Narration and voiceover
Use built-in voices for narration, explainer videos, or voiceovers where a specific cloned voice isn't required.