Text-to-speech with feeling - this new AI model does everything but shed a tear

ElevenLabs has introduced v3, its most expressive text-to-speech model yet. The new AI can exhibit a wide range of emotions and subtle communicative quirks like sighs and laughter, making its speech more humanlike. V3 can speak over 70 languages and is customizable through "audio tags" that modify output. This development represents a significant advancement in AI-generated voice technology, potentially changing how humans interact with machines in the future. However, some users may find the excessively animated voices unsettling.