DomoAI Enhances Talking Avatar Feature: Now Supporting Emotional and Conversational Expressions for Integrated Video Production
DomoAI has updated its Talking Avatar feature, enabling integrated video production from generation to direction and conversation.
📋 Article Processing Timeline
- 📰 Published: March 31, 2026 at 20:30
- 🔍 Collected: April 1, 2026 at 13:39 (17h 9m after Published)
- 🤖 AI Analyzed: April 17, 2026 at 04:30 (374h 51m after Collected)
DomoAI PTE. LTD. (Headquarters: Singapore, CEO: Joe Lam, hereinafter 'DomoAI'), operator of the AI video and image generation platform 'DomoAI,' has announced the release of an update to its 'Talking Avatar' feature. This update enhances voice, emotion, and conversational expressions, allowing for the creation of content with narrative and directorial depth in addition to standard video generation. Users can now manage the entire workflow from generation to direction and conversation in a single, integrated process. This environment enables the seamless production of videos where characters move and speak.
Key Updates to the Talking Avatar Feature:
Talking Avatar is a feature that generates characters from images or videos and creates natural talking videos using only text input. It allows for the creation of conversational content by adding voice and expressions to characters without the need for recording.
- Improved Voice Quality (Natural Voice Model): Achieves more human-like vocal expressions.
- Addition of Emotional Expressions (Emotion Control): Tone settings such as 'hope,' 'whisper,' and 'anger' can be applied to each line.
- Realization of Conversational Generation (Multi-voice): Set multiple voices to generate dialogues between characters.
- Smart Paste Function (Automatic Script Splitting): Automatically splits input text by role.
- Video Upload Support: Supports input of video materials in addition to portrait images.
Production Workflow:
1. Material Generation: Generate video from images or create video materials from multiple images.
2. Direction: Apply style transfers or add character movement.
3. Conversational Expression: Add voice and dialogue using the Talking Avatar feature.
About DomoAI:
DomoAI is a global technology company based in Singapore providing a next-generation AI animation platform. Since its 2023 release, it has surpassed 3 million users and is recognized as a leading AI creative platform, recently receiving the 'Singapore SME 500 Award' in 2025.
Key Updates to the Talking Avatar Feature:
Talking Avatar is a feature that generates characters from images or videos and creates natural talking videos using only text input. It allows for the creation of conversational content by adding voice and expressions to characters without the need for recording.
- Improved Voice Quality (Natural Voice Model): Achieves more human-like vocal expressions.
- Addition of Emotional Expressions (Emotion Control): Tone settings such as 'hope,' 'whisper,' and 'anger' can be applied to each line.
- Realization of Conversational Generation (Multi-voice): Set multiple voices to generate dialogues between characters.
- Smart Paste Function (Automatic Script Splitting): Automatically splits input text by role.
- Video Upload Support: Supports input of video materials in addition to portrait images.
Production Workflow:
1. Material Generation: Generate video from images or create video materials from multiple images.
2. Direction: Apply style transfers or add character movement.
3. Conversational Expression: Add voice and dialogue using the Talking Avatar feature.
About DomoAI:
DomoAI is a global technology company based in Singapore providing a next-generation AI animation platform. Since its 2023 release, it has surpassed 3 million users and is recognized as a leading AI creative platform, recently receiving the 'Singapore SME 500 Award' in 2025.
FAQ
What can I do with the Talking Avatar feature?
You can generate characters from images or videos and create natural talking videos with voice and expressions just by entering text.
How do I set emotional expressions?
You can select tones such as 'hope,' 'whisper,' or 'anger' for each line of dialogue to fine-tune the character's performance.
Can I upload video materials?
Yes, you can input not only portrait images but also video materials to use as a Talking Avatar.