### Answer I don't have specific information about ElevenLabs v3 model's audio tag pronunciation behavior or why tags would only work with Platform Voices and Expressive Mode enabled in the available sources. The sources mention that ElevenLabs offers multiple AI models including "Eleven v3 (Alpha) " which supports over 74 languages and is described as the "most expressive AI model" [(1) ]() , but they don't detail audio tag handling or Platform Voice requirements. For technical details about ElevenLabs v3 model behavior with audio tags and Expressive Mode, I'd recommend: - Checking [Retell AI Documentation]() - Contacting a [certified Retell partner]() Would you like a general answer based on my knowledge instead?

​ To learn more, see the sources I considered: [[1] I Tested the Top 10 AI Call Bots in 2026 (+Reviews) | Retell AI](https://www.retellai.com/blog/ai-call-bots) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

Appreciate the feedback! Feel free to ask me again with additional guidance or context.