ElevenLabs Launches Multilingual Generative AI Voice Model

Synthetic voice AI startup ElevenLab has launched its tools out of beta with a 28-language generative AI model called Eleven Multilingual V2. The foundational AI model offers voice clones and synthetic voices in those languages with enhanced realism and can identify a spoken language to transcribe it automatically without any typing first.

ElevenLabs Speaks

ElevenLabs employs generative AI voice models created from scratch or cloned from existing voices. The startup raised $19 million in June and debuted a tool for detecting the sound of its synthetic voice models. With Eleven Multilingual V2, the company is building on its prior work analyzing how different languages and emotions sound to give the AI the capacity to recognize both across the 25 languages joining the existing English, Spanish, and Portuguese.

ElevenLabs leveraged extensive in-house research to create the model, reflecting its mission to make content accessible in any language and voice via AI. It believes that AI can help break down linguistic barriers to creativity and innovation. Users can now replicate their speech across nearly 30 tongues with the multilingual model. ElevenLabs envisions a wide use of its tools by game developers, teachers, and content creators for translation, localizing audio content, and teaching languages. The company also wants to market the tech for helping people with impaired vision access written content in multiple languages. Its current partners include generative AI video startup D-ID, audiobook publisher Storytel, digital content host TheSoul Publishing, and game companies Embark Studios and Paradox Interactive.

“ElevenLabs was started with the dream of making all content universally accessible in any language and in any voice. With the release of Eleven Multilingual v2, we are one step closer to making this dream a reality and making human-quality AI voices available in every dialect,” ElevenLabs CEO Mati Staniszewski said. “Our text-to-speech generation tools help level the playing field and bring top quality spoken audio capabilities to all the creators out there. Those benefits now extend to multilingual applications across almost 30 languages. Eventually we hope to cover even more languages and voices with help of AI, and eliminate the linguistic barriers to content.”

Follow @voicebotaiFollow @erichschwartz

Generative AI Speech Startup ElevenLabs Raises $19M and Releases Deepfake Voice Detector

Generative AI Video Startup D-ID Partners with Deepfake Voice Startup ElevenLabs

Synthetic Speech Startup ElevenLabs Raises $2M for AI Voices With Context-Relevant Emotion