Hedra teams up with ElevenLabs to give voice to video

The future of storytelling

Hedra just emerged from stealth with their Character-1 model that allows users to generate a video of a character from a still image in seconds. Within 48 hours of launching, Hedra had tens of thousands of users producing over 100,000 generations. Character-1 is the first of a slate of foundational models for creators to imagine characters, stories and worlds. To get an idea of Hedra’s capabilities, see some community creations on their socials, try the free beta on their site, or check out this sample from Ryan Morrison:

At ElevenLabs, we imagine a future where every character, story, and article comes alive with engaging audio. Hedra is helping us make this vision a reality by integrating our AI voices into their video creation tools.

Realistic, emotional character voices

When looking for a partner to power the voices behind their AI characters, Hedra was looking for an industry leader that could handle their exponential growth and provide customers with a large and diverse selection of high quality voices. After reaching out to ElevenLabs, Hedra was up and running in a few days. In the first week alone, Hedra served over 76,000 users without a single hiccup. 

“Our goal at Hedra is to make it easy for anyone to tell stories, create characters, and build worlds, through video. Partnering with ElevenLabs helped us accelerate our mission by making it easy for creators to generate human-like, immersive voiceovers”. Michael Lingelbach, founder & CEO at Hedra

About Hedra

Hedra is a creation lab that integrates advanced AI video models into products, revolutionizing human storytelling. The research preview, Character-1, allows users to generate expressive and controllable human characters in videos. This tool is designed to democratize video creation, enabling anyone to imagine worlds, characters, and stories with complete creative control.

About ElevenLabs

At ElevenLabs, we research and build audio AI tools for creators, media, and businesses. Our models use proprietary methods for context awareness and high compression to deliver lifelike, compelling, and nuanced speech, voices, and sound effects across 29 languages. Our AI tools voice audiobooks and news articles, animate video game characters, assist in film pre-production, automate localisation processes in entertainment, create dynamic audio content for social media and advertising, and train medical professionals.