Text-to-speech models from ElevenLabs, Hume AI, and Descript are all pushing the limits of AI-generated voice technology.

Voicing AI, a young Silicon Valley startup building 'agentic' AI for enterprise voice automation, says its newest speech model now responds in under 70 milliseconds — faster than the blink of an eye, ...

Built on the advanced StyleTTS2 architecture, it delivers high-quality voice synthesis despite being trained on less than 100 hours of audio, and it runs efficiently even on systems without a GPU.