Synthetic Voice AI Startup ElevenLab Launches Multilingual Generative AI Voice Model
ElevenLab, a synthetic voice AI startup, has announced the launch of its tools out of beta. The company’s latest offering is Eleven Multilingual V2, a generative AI model available in 28 languages. The model provides voice clones and synthetic voices with enhanced realism and the ability to automatically transcribe spoken language without the need for typing.
ElevenLabs Voices
ElevenLab utilizes generative AI voice models that are either created from scratch or cloned from existing voices. In June, the startup raised $19 million and introduced a tool for detecting the sound of its synthetic voice models. With Eleven Multilingual V2, the company expands on its previous work by incorporating the capacity to recognize different languages and emotions across the 25 languages, in addition to English, Spanish, and Portuguese.
Breaking Linguistic Barriers
ElevenLab’s mission is to make content accessible in any language and voice through AI. The company believes that its AI technology can help overcome linguistic barriers, fostering creativity and innovation. The multilingual model allows users to replicate their speech across nearly 30 languages, making it beneficial for game developers, teachers, content creators, and individuals with impaired vision. ElevenLab’s current partners include D-ID, Storytel, TheSoul Publishing, Embark Studios, and Paradox Interactive.
Making Human-Quality AI Voices Universally Accessible
ElevenLab’s CEO, Mati Staniszewski, expressed the company’s vision of making all content universally accessible in any language and voice. With the release of Eleven Multilingual V2, the company takes a step closer to this goal by offering human-quality AI voices in almost 30 languages. The text-to-speech generation tools provided by ElevenLab aim to provide top-quality spoken audio capabilities to content creators and eliminate linguistic barriers to content.