Google TTS (Gemini) now supports streaming — any p...
# agents
a
Google TTS (Gemini) now supports streaming — any plans to integrate it into LiveKit? Hey team, Google’s new TTS (Gemini) has recently come out of beta and now supports streaming speech synthesis. It looks like it could offer faster response times and improved voice quality compared to the existing Google Cloud TTS integration. Is there any plan to add support for the Gemini TTS API (especially the streaming mode) in the near future? It would be great to know if this is on the roadmap or if there’s any guidance for experimenting with it through LiveKit’s current TTS abstraction layer. Thanks!
👀 2
a
Thank you for the note @refined-appointment-81829. As you can see, the beta gemini is hard-coded to streaming=False. That's a big blocker for gemini TTS.
@stale-thailand-88613 Any thoughts on this?
r
You can follow this ticket for updates: https://github.com/livekit/agents/issues/3864
I saw a branch related to that
a
I opened the ticket. I didn't see a branch. I saw a related PR that was merged in Pipecat if that helps as a reference. https://github.com/pipecat-ai/pipecat/pull/3039
a
any update here? @refined-appointment-81829? This is by far the best TTS, would be very helpful to get it
r
No, Best to ask in this ticket so communication can be consolidated https://github.com/livekit/agents/issues/3864