Introduce a product.
Tell viewers who it’s for, what it helps them do and what to try next. The Clico example above turns that kind of introduction into a presenter clip.
AI Talking HeadVideo Generator
Create a talking head video from a photo and your recording. Give your AI avatar a voice for product introductions, explainers and welcome messages.
Create your AI avatar video
Photo + voiceMaya, a fictional AI avatar in a sage green sweater, speaks directly to the camera with small hand gestures and a steady studio background. She introduces Clico’s scripts, images, video and voice tools. Created in Clico from the portrait and supplied voiceover.
A speaking presenter.
Without a new camera take.
Your AI avatar starts with a portrait: your own photo or a fictional presenter you create in Clico. Add a finished recording to make a talking head video, then choose how the presenter moves.
A face you choose.
Use a photo of yourself or an AI presenter. The portrait gives the video its appearance, clothing and setting.
The words and voice you supply.
Your recording sets the speech and timing. Use your own voice, or create a voiceover in Clico before making the video.
Room to direct the delivery.
Choose subtle, balanced or expressive movement. Add optional direction for the performance, then review the generated result.
Give your next message a presenter.
Start with what you want someone to understand. A talking head can deliver the introduction, explanation or welcome at the heart of your video.
Explain one idea.
Give a lesson, walkthrough or FAQ a speaker. Use the presenter for the explanation, then pair the clip with slides or screen recordings in your edit.
Welcome your audience.
Create an onboarding message, course introduction or community update. Reuse your chosen portrait with a new recording when the message changes.
How to make an AI talking head video.
Create your AI avatar’s portrait, give them a voice, then bring both together in Clico. Already have a photo or recording? Use your own file for that step.
Create a talking head video01Create your presenter’s portrait.
Start with who should speak and where the video will appear. Clico can turn that idea into a fictional presenter image.
- Describe the presenter. Tell Clico the look, clothing, setting and framing you want. Let the chat develop the image prompt with you.
- Choose and save one image. Check that the face is clear and the pose leaves room for movement. Download the JPG, PNG or WebP you want to animate.
The original AI presenter image used in this example. 02Turn your message into a voiceover.
The recording supplies the exact words, voice and length of the video. Make it sound right before you animate the presenter.
- Write the message. Bring a script, or tell Clico your audience and what they should hear so it can help you write one.
- Generate and listen. Choose the language and delivery in chat. Listen for pronunciation, pauses and pacing, then revise the recording if needed.
- Save the final audio. Download an MP3 or WAV, between 1 and 120 seconds and up to 8 MiB. You can also record your own voice.
The script and voiceover used in this example. Hi, I'm Maya. Got an idea? Bring it to Clico. Together, we'll shape it into scripts, images, video, and voice, all in one creative conversation. Let's make something great.
This AI voiceover was generated in Clico.
03Generate the talking head video.
Bring your chosen portrait and final recording back to the creation form. Animate your AI avatar into a talking head video with the voice and message you supplied.
- Add both files. Upload the portrait and audio above. Preview the recording to check that it is the version you want.
- Set the frame and movement. Choose 16:9, 9:16 or 1:1 and 720p or 1080p. Fit or crop the portrait, choose movement intensity, and optionally add motion direction.
- Review and generate. Continue in Clico with your files and video settings. Sign in, review the credit cost and send the draft.
- Watch, then download. Check the lip movement, expression and timing. If the words need changing, revise the audio and generate again. Download the finished MP4.
The finished video, made from the portrait and voiceover above.
One clip. Ready for your next edit.
Download an MP4 with your speech included. Use it as a standalone message, or bring the presenter into a longer video. Create other scenes with Clico’s AI video generator.
Choose the shape before you generate.
- Landscape 16:9For wide video layouts
- Square 1:1For square video layouts
- Portrait 9:16For vertical video layouts
Output shape options shown. Fit the whole portrait or crop to fill your chosen frame.
- Video file
- MP4 with your supplied speech
- Length
- 1–120 seconds, set by your audio
- Quality
- 720p or 1080p
Add captions, music or screen recordings in your editing workflow. If the message changes, update the audio and generate a new presenter clip.
Choose my video settingsBefore you make your video.
What’s the difference between a talking head video and an AI avatar?
A talking head video shows a presenter speaking to the camera. An AI avatar is the digital presenter who appears in that video. In this tool, your avatar starts with a portrait of you or a fictional presenter; your recording supplies the words and voice. Reuse the portrait with a new recording when your message changes.
Can I start with a written script?
Yes. Use Create a voiceover to work on your script and generate speech in Clico. Download the final MP3 or WAV, then upload it with your portrait in this page’s creation form. The recording supplies the spoken words; you do not need to write a video prompt.
What makes a good photo and recording?
Use a clear image of one person with an unobstructed, well lit face, plus a recording with clearly audible speech. This form accepts JPG, PNG or WebP images and MP3 or WAV audio, up to 8 MiB per file. Recordings must be between 1 and 120 seconds.
Can I change the words or voice after generating?
The spoken words and voice come from your recording. To change them, prepare a revised recording and generate another video with your portrait. Changing the optional motion direction does not rewrite the speech.
How much control do I have over the performance?
Choose subtle, balanced or expressive movement and optionally describe motion in words. These guide the generated performance; they do not set exact gestures for individual words. Review the lip movement, expression and timing in the finished video.
Is it free to generate a video?
You can preview the example and prepare your files here. Generating a video in Clico requires a paid plan and uses credits. Sign in and review the generation cost before sending your draft.
Can I use my own portrait or an AI presenter?
You can use a portrait of yourself or a fictional presenter. Only upload images and recordings you have permission to use. The example on this page uses a fictional AI presenter, not a customer testimonial.
Ready to give your message a face?
Bring your presenter image and voiceover. Review the settings, then create your video in Clico.
Create my talking head