Inworld AI launches Realtime TTS-2 model for live conversations
SMRTR summary
Inworld AI has launched Realtime TTS-2, a voice model built specifically for live conversation rather than scripted narration. It responds in under 200 milliseconds, adapts to emotional tone across exchanges, supports 100+ languages with a consistent voice identity, and accepts natural-language direction — making AI conversations feel genuinely human.
SMRTR provides this summary for quick context. The original article belongs to Testing Catalog.
Read the original article