Gemini 2.0 Flash now available

Gemini 2.0 Flash is now available to all developers. If you read the official announcement from Google you'll see a number of benefits, especially for those building conversational AI agents.

Google's latest Gemini model, Gemini 2.0 Flash has a very fast Time To First Token (TTFT), great instruction following, and reliable function calling. All of this makes it the perfect brain for your agents.

As well as Gemini 2.0 Flash, ElevenLabs Conversational AI currently supports the following models out of the box:

• Gemini 2.0 Flash
• Gemini 1.5 Flash
• Gemini 1.5 Pro
• Gemini 1.0 Pro
• GPT-4o Mini
• GPT-4o
• GPT-4 Turbo
• GPT-3.5 Turbo
• Claude 3.5 Sonnet
• Claude 3 Haiku

While ElevenLabs Conversational AI includes a number of built-in models, you can also use your own model thanks to the Custom LLM option. This allows you to provide any OpenAI-compatible API server, providing support for popular open source models like Llama 3.3 or DeepSeek R1 through hosting providers like Cloudflare Workers AI, Groq Cloud, and Together AI.

Start building realtime conversational AI agents with Gemini 2.0 Flash now: elevenlabs.io/conversational-ai