Skip to content
Inworld AI Blog· The Inworld TTS team·· 25 d agoPickAI score50

Inworld updates Realtime TTS-2 with reasoning mode, faster speed and more consistent voices

Realtime TTS-2 updates: reasoning, speed and consistency

AI summary

Inworld has rolled out two updates to Realtime TTS-2. The optional Reasoning feature has the model write performance directions from context before synthesis. The updated model keeps the existing model ID. According to Inworld's comparison with the previous version, short utterances generate about 13% faster and medium-length ones about 9% faster, and cloned-voice similarity has improved along with fewer dropped words in long text. TTS-2 currently supports single and asynchronous synthesis, with WebSocket streaming, duplex and batch synthesis coming soon.

Why it matters

Instead of fixed emotion tags, it lets the model write its own performance directions from context, though WebSocket streaming and full-duplex access will come later.

Source: Inworld AI Blog · inworld.ai