_.png "The Best Mushroom Coffee")
ElevenLabs announced the language expansion of its latest artificial intelligence (AI) text-to-speech (TTS) model last week. With this expansion, the AI model now supports 41 new languages, taking the total count to 70 supported languages. The New York City-based AI startup said that with this expansion, the model is now accessible to 90 percent of the global population. Notably, the company released the Eleven V3 (alpha) model on June 8, and pitched it as its “most expressive TTS model.”
Eleven V3 Now Supports 70 Languages
In a post on X (formerly known as Twitter), the official handle of ElevenLabs announced that their latest AI model, Eleven V3, now supports an additional 41 languages. With this update, the model can natively generate audio from text scripts in a total of 70 languages. Some of the newly added languages include Arabic, Assamese, Bengali, Bulgarian, Catalan, Gujarati, Latvian, Malay, Malayalam, Marathi, Nepali, Swahili, Tamil, and Telugu.
The company advised that those wanting to generate text in any of the new languages should record an Instant Voice Clone (IVC) while selecting the language. Additionally, ElevenLabs is also adding Voice Library voices for the new languages in the coming weeks.
Eleven V3 is the successor to the multilingual V2 and V2.5 TTS models. The latest AI model supports inline audio tags such as whispers, excited, sighs, and more. Adding audio tags enables the model to add expressive emotional nuances, non-verbal cues, and dramatic delivery to the audio generation.
It also supports multi-speaker intractions with interruptions, natural pacing, and overlapping dialogues. Additionally, the company says the model better handles elements such as stress, cadence, and contextual awareness. The Eleven V3 is available via the company’s website and mobile apps. It is currently not available as an application programming interface (API).
In April, ElevenLabs introduced a new enterprise-focused agentic feature dubbed Agent Transfer. Part of the company’s Conversational AI, it lets two AI agents to communicate and share conversations. The feature creates a system where one AI agent can hand over a conversation to another, more specialised agent, along with the conversation data.
