Antzoki-TTS: Adding Emotion and Acting Capabilities
Traditional Text-to-Speech technology gives us solid voices today, but offers no way to guide the interpretation of the audio. If we want to use these models to produce audiobooks, stories, game audio, etc., we soon realize the results are not ideal. We get cold, neutral voices. Robotic. Boring. Lately, however, models that allow us to specify paralinguistic cues (pauses, breathing, and emotional variations) are beginning to emerge. Thanks to this technology, by providing script-like instructions, we can create emotionally rich synthetic voices. ...