Google has just launched its new Gemini 2.0 Flash model, featuring seamless voice-to-voice conversation capabilities. We wasted no time integrating it into our platform—perfectly aligning with our Conversation Agents Connector initiative.

With Voximplant handling all audio processing and providing a serverless architecture, developers can now connect telephony to Gemini-powered agents in minutes. Just write a simple JavaScript scenario to manage prompts, tool calling, and real-time message handling with Gemini.

Switching between voice and text output is effortless. And for text-to-speech, our ElevenLabs Streaming integration offers a vast library of high-quality voices for real-time TTS synthesis, giving developers plenty of options.

To experience the Gemini 2.0 Flash Live API Client in action, call 1-888-927-7255 and try our demo. 

ElevenLabs has launched its WebSockets API and the ultra-fast Flash 2.5 model, enabling low-latency streaming speech synthesis – perfect for giving voice to LLM responses. By streaming text chunks in real time, audio generation begins almost instantly, making delays virtually unnoticeable.

You can use it in VoxEngine scenarios – either standalone or alongside OpenAI or Gemini integrations

Learn more in our Gemini Live API Client Guide and Realtime Speech Synthesis Guide.