The Retell Community is where innovators, call center leaders, and AI enthusiasts come together to share ideas, learn best practices, and explore the future of voice automation. Join to connect with peers, get early access to product updates, and collaborate on building human-like AI voice experiences that transform customer service.

Retell AI

Hey team! 🙌 First of all, huge thanks for adding Gemini 3.1 Flash-Lite — really excited to test it out!

I've been checking the detail logs when using this model and I noticed it still shows the standard ASR → LLM → TTS pipeline breakdown. That got me curious — since Google also just released `gemini-3.1-flash-live-preview`, which is their native audio-to-audio (A2A) model (similar to how you integrated OpenAI Realtime), is there any plan to support that version as well?

The reason I ask is that a native voice-to-voice model would skip the ASR/TTS overhead entirely, which could be a significant latency improvement for real-time call use cases.

Thanks in advance! 🚀 <@1074218598458994738> <@&1387275965486465074> <@605090813025976344>