DomoAI Launches TTS and Integrates OpenAI's GPT Image 2.0 in Talking Avatar Workflow 

DomoAI, providers of a generative artificial intelligence video platform, has added built-in text-to-speech to its Talking Avatar platform.

With DomoAI's Talking Avatar, users drop in or generate an image, type a script, pick a voice, and hit generate. Or users could upload the voice themselves. The output comes with the lip sync already aligned. And now with its built-in text-to-speech (TTS) functionality, all operations can be completed on a single screen.

DomoAI also recently integrated OpenAI's GPT Image 2.0 so creators can generate the source image, animate it, voice it, and upscale it in one platform.

"They've been around since creators started using them daily to publish content. Two years ago, creating a clear and smooth avatar video would take an afternoon, stringing together multiple tools. Now, it can be done in just a few minutes within a single app," said Joe Lam, CEO of DomoAI, in a statement. "The voice is key. In the past, they sounded entirely like AI voices, but not anymore. We've added emotion control features, allowing creators to adjust the tone of voice appropriately rather than struggling with a flat, monotonous sound."