Use your voice to produce talking head videos

By EngineAI Team | Published on October 1, 2025 | Updated on January 23, 2026
Use your voice to produce talking head videos
This video will show you how to make great talking avatar presentations by using Google Gemini to build a headshot and Wan Video to animate it with your voice—no filming is needed. 

In detail: "Give me a professional headshot of this person as a talking head, facing the camera, wearing [outfit], with [background]" is the question that appears when you upload a photo to Gemini, excellent quality, expert lighting, and close-up shot. 

Go to create.wan.video, make a new project, and select Avatar as the media type instead of Video. 

Add audio by recording ten to fifteen seconds of your script or typing up to 300 words to utilize Wan's built-in voices after uploading your Gemini headshot. 

After selecting "Generate" to synchronize your lip movements with your audio, click "Send to Timeline" and use the "+" button to add segments to create your entire video. Before you begin, write your script and divide it into manageable chunks with organic breaks. 

 Each footage flows naturally as a result, giving the impression that the presenter is authentic.

Your one-stop shop for automation insights and news on artificial intelligence is EngineAi.
Did you like this article? Check out more of our knowledgeable resources:
📰 In-depth analysis and up-to-date AI news .
🤝 Visit to learn about our goal and knowledgeable staff.
📬 Use this link to share your project or schedule a free consultation.
Watch this space for weekly updates on digital transformation, process automation, and machine learning. Let us assist you in bringing the future into your company right now.

🔗 External Resource:
Visit Link →