ElevenLabs has recently released ‘Eleven Multilingual v2’ a foundational deep learning AI model that supports 28 languages with advanced multilingual capabilities.
The new voice generation model is capable of producing accurate AI audio outputs in 28 languages. Consequently, it can automatically identify various written languages and easily generate speech.
According to ElevenLabs, the languages covered includes; Bulgarian, Classical Arabic, Chinese, Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, German, Greek, Hindi, Indonesian, Japanese, Italian, Korean, Malay, Polish, Portuguese, Romanian, Slovak, Spanish, Swedish, Tamil, Turkish and Ukrainian.
Furthermore, this recent launch marks their transition out of Beta and they plan to “make content universally accessible in any language and voice” moving forward.
This will allow their voice AI software to reach more users across the world and improve the accessibility and capability of their AI-powered services.
In a recent tweet, they have officially introduced the new version of their AI speech model.
Now, users can access the updated voice generator with enhanced conversational capability and higher output quality.
In addition, they also released a demonstration video showcasing how the multilingual model works.
The voice AI platform exerted a lot of effort in building an AI model that better understands context and has the ability to convey ‘emotionally rich’ audio outputs.
Moreover, a unique synthetic voice or the user’s cloned voice may be used and maintained to the generated speech content across all languages.
“Eventually, we hope to cover even more languages and voices with help of AI, and eliminate the linguistic barriers to content. At ElevenLabs, we believe these leaps in accessibility will ultimately foster greater creativity, innovation, and diversity,” Mati Staniszewski, CEO of ElevenLabs said in a release.
ElevenLabs continues to stand out as the leading voice AI generation software that consistently provides cutting-edge improvements on their multilingual model.
Aside from being able to turn text into speech in 28 languages, they also offer a professional voice cloning feature allowing users to use their own voice in speech generation. Imagine hearing your voice speaking in 28 languages – a total gamechanger!