ElevenLabs launches Eleven v4, its most expressive voice model
In 30 seconds
ElevenLabs launched Eleven v4, its most expressive text-to-speech model, and Eleven v4 Turbo, a low-latency variant designed for agents. Both support more than 90 languages, including Spanish and Catalan. With Eleven v4, tags inside the text indicate how to say a phrase, what emotion to convey and even sound effects.
According to ElevenLabs, voice agents have until now forced a choice between speed and expressiveness.
On September 28, ElevenLabs launched Eleven v4, its most expressive text-to-speech model, and Eleven v4 Turbo, the low-latency variant designed for agents. Both support more than 90 languages, including Spanish and Catalan. With Eleven v4, you can use tags inside the text to indicate how certain phrases should be said, what emotion to convey and even sound effects.
For a small business, this means voice agents that answer calls with a more natural, less robotic tone, without losing speed. ElevenLabs optimized the Turbo version together with ElevenAgents, its conversational agent platform.
At InfinyAI we work with voice and AI, and we are going to test it thoroughly. Would you put an agent like this in front of your customers?
Why it matters
A voice agent that answers calls can sound more natural without losing speed.
Official source: ElevenLabs
