Creative Reality studio Expressions

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

Synthetic media startup D-ID will augment the AI-generated videos produced in its Creative Reality Studio with original voices produced from generative AI speech startup ElevenLabs. Users will be able to bring ElevenLabs’ expressive voices to their videos, matching them to the animated avatars and visuals that D-ID’s proprietary generative AI engine shows.

D-ID ElevenLabs

D-ID’s Creative Reality Studio offers users the chance to design video avatars based on uploaded photographs or from synthetically generated images produced by Stable Diffusion’s text-to-image engine. The avatar is then matched to a script written by the user or composed by a text generator powered by OpenAI’s large language models. Though users could already pick the language, voice, and manner of speaking they want, ElevenLabs’ audio will enable more lifelike vocal performances that convey emotion and personality in alignment with the visuals. This provides a major upgrade over default text-to-speech, enhancing production value for creators.

“We are very pleased to be partnering with ElevenLabs, providing the creator community with further power and ease to combine various generative AI tools,” D-ID CEO Gil Perry said. “With a subscriber to our studio every two seconds on average, we have seen some imaginative and inspirational videos, and our collaboration with ElevenLabs means our users will easily access higher-quality voices.”

Synthetic voice AI startup ElevenLabs employs generative AI voice models created from scratch or cloned from existing voices using small voice samples to breathe life into digital avatars. The startup raised $19 million in June and debuted a tool for detecting the sound of its synthetic voice models. D-ID joins a growing list of ElevenLabs partners, including audiobook publisher Storytel, digital content host TheSoul Publishing, and game companies Embark Studios and Paradox Interactive.

“We are very excited to join a leading player in the text-to-video field like D-ID,” ElevenLabs CEO Mati Staniszewski said. “Many customers use our voices to bring digital people and avatars to life. Collaborating with D-ID is a natural progression and response from users to merge our market-leading voice technology together with D-ID’s top rated text-to-video tech.”

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

D-ID Launches Chat API to Give Generative AI Chatbots a Face and Voice

Synthetic Media Startup D-ID Launches Image-to-Video Platform