DomoAI Adds Text to Speech and GPT Image 2.0 Integration to Talking Avatar Tool

DomoAI has added built-in text to speech and integrated OpenAI's GPT Image 2.0 into its Talking Avatar workflow, announced in a press release. The update allows creators to generate, animate, voice, and upscale AI avatars within a single interface.

The Talking Avatar feature enables users to upload or generate an image, enter a script, select or upload a voice, and produce a video with automatic lip sync in about one minute. The tool supports continuous video output of up to 60 seconds and now includes emotion control for the voice, letting creators adjust tone and expression.

DomoAI reports that more than four million creators use its generative video platform. The company noted strong adoption in Japan among VTuber and anime creators who use Talking Avatar to give voice to their characters. Music video creators have also used the feature to animate and voice characters within a single workflow.

According to CEO Joe Lam, the integration simplifies tasks that previously required multiple tools and extended production time. The unified workflow is aimed at creators producing scripted content such as educational videos, marketing clips, and online performances.