CryptoWorld News reports that Inworld AI has released the real-time conversational speech synthesis model TTS-2, which can adjust its voice based on the tone of the conversation. Its predecessor, TTS-1.5, ranked first on third-party evaluation platforms, surpassing Google and ElevenLabs. TTS-2 introduces four new core capabilities, including conversational awareness, natural language speech guidance, cross-language consistency, and text-to-voice creation. The model supports 15 official languages and over 90 experimental languages, and has been integrated into platforms such as Cloudflare, LiveKit, and DeepInfra. CEO Kylan Gibbs stated in an interview with Business Insider that Inworld only develops models and APIs, not consumer products, to avoid competing with its clients.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin