Inworld Releases Realtime TTS-2 and TTS-2 Flash Models

Inworld has launched two new text-to-speech models: Realtime TTS-2, which prioritizes audio clarity and realistic voice cloning, and TTS-2 Flash, designed for ultra-low latency and high volume. The Flash version supports over 200 languages and achieves a first-byte latency of just 20 milliseconds.