The recent AI boom knows no bounds and is being utilized in various fields.
From easily retouching personal photos to turning them into videos...
In an era where small ideas easily take shape, I study every day so as not to be left behind.
In the midst of this, DomoAI, an AI video and image generation platform operated by DomoAI PTE. LTD, has updated its Talking Avatar feature.
This allows for the creation of content involving stories and direction, moving beyond conventional video generation.
Enhanced DomoAI Supports AI Video Generation
PR TIMESThe Talking Avatar feature of the AI video and image generation platform DomoAI is a function that can generate characters based on images or videos to create movie clips.
No recording is required, and conversations can be directed exactly as the entered text.
With this update, expressive elements such as voice, emotion, and conversation have been strengthened.
The main update details for the Talking Avatar feature are as follows:
- Improved Voice Quality: Achieving more human-like vocal expression
- Addition of Emotional Expression: It is now possible to set tones such as Hope, Whisper, and Anger for each line
- Realization of Conversation Generation: It is now possible to set multiple voices and generate dialogue between characters
- Smart Paste Feature: Automatically splits entered text by role
- Support for Video Uploads: Now supports video material input in addition to portrait images
Expanding Production Flow as a Foothold for Creating New Content
With the update of the Talking Avatar feature, DomoAI has made further leaps forward.
As an example, here is a flow for producing a video where characters converse in DomoAI.
First, create a video using the Image-to-Video or Text-to-Video functions from the AI Video mode on the official DomoAI website.
By naturally joining two images together or preparing a movement video separately from the model's illustration, it is possible to move the avatar accordingly.
Next, use the enhanced Talking Avatar feature to breathe a voice into the image or video avatar.
By supplementing the avatar's movements and facial expressions with prompts, the footage becomes even higher quality.
Also, if you do not have audio for them to speak, you can use the Text-to-Speech function to create audio files for one or two people.
In other words, the entire sequence of video production—generation, direction, and conversation—is completed within DomoAI alone.
DomoAI PTE. LTD. is a global technology company based in Singapore.
Since its release in 2023, DomoAI has rapidly accelerated its presence, with the number of users surpassing 3 million.
Furthermore, more than 1.3 million people participate in the Discord server, ranking it in the world's top 10.
For details on the service, please check the official DomoAI website and official X (@DomoAI_).
Hey Domos,
TTS just got a big update.
✨New natural voice model
✨Emotion control — Hopeful, Angry, Whispering, or your own prompt
✨Multi-voice conversations from single scriptOne script. Endless voices. Full tone control.🎙️
Try Now: https://t.co/uerQQTPEKQHave fun!… pic.twitter.com/6YDpPknxPa
— DomoAI official (@DomoAI_) March 19, 2026
