Configure Voice – Voice Model

Choose the voice model your AI agent will use

You can currently choose from these 4 models:

• Elevenlabs Flash V2.5

  Ultra-fast model optimized for real-time use (~75 ms)

• Elevenlabs Turbo V2

  High-quality, low-latency model with a good balance between quality and speed (~250–300 ms)

• Elevenlabs Turbo V2.5

  High-quality, low-latency model with a good balance between quality and speed (~250–300 ms); in English, it’s 25% faster than Turbo V2.

• Elevenlabs Multilingual V2

  Most realistic model with rich emotional expression

---

Choose the model that best suits your agent’s purpose — we recommend doing a test run so you can see how it performs in real-time.