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

<@1145576664366055464>  are gemini live models supported?

Thanks for tagging me <@235200428940328964>. I'll look through relevant sources and get back to you shortly.

### Answer
 

Based on the available documentation, Retell AI supports the following **Google Gemini text LLM models**: [(1) ](<https://docs.retellai.com/api-references/update-retell-llm>) [(2) ](<https://docs.retellai.com/api-references/list-retell-llms>)

- `gemini-2.5-flash`
- `gemini-2.5-flash-lite`
- `gemini-3.0-flash`

For **speech-to-speech (S2S) models**, only OpenAI realtime models are listed as available options: 

- `gpt-4o-realtime`
- `gpt-4o-mini-realtime`
- `gpt-realtime`
- `gpt-realtime-mini`

I don't have information in the sources about "Gemini Live" models (Google's native audio/multimodal models) being supported as S2S options on Retell AI. The Gemini models currently available are text-based LLMs, not native audio models.

If you're looking for native audio capabilities similar to what Gemini Live offers, the OpenAI realtime models listed above are the current S2S options. [(1) ](<https://docs.retellai.com/api-references/update-retell-llm>)

​
To learn more, see the sources I considered:

[[1] Update Retell LLM](https://docs.retellai.com/api-references/update-retell-llm)
[[2] List Retell LLMs](https://docs.retellai.com/api-references/list-retell-llms)
​

Feel free to tag <@1145576664366055464> with additional questions. I also appreciate feedback, it helps me improve.