Make an ai talking photo from one person’s picture: choose a scene and MiniMax H3 creates a 15-second vertical video with environmental sound and instrumental music, but no spoken voice.
1أضف صورتك
2الجودة والمدة768p · 15s · 9:1660 credits
بدون اشتراك · جاهز خلال 3 دقائق تقريبًا · لا يتم الخصم إذا فشل
Upload a photo of yourself or an adult who has agreed to appear. Do not upload someone else’s image without their consent.
From the Feed
These six presets give one person’s photo an ai talking photo setting: Portrait Says Hello, a warm home, a pet at the person’s side, a birthday backdrop, a decorated holiday room, or a table-side reaction. Portrait Says Hello is selected by default. Select a scene in the tool, then upload one person’s photo. Each result is a 15-second vertical video with environmental sound and instrumental music, without a human voice. The presets set the scene; they do not accept a custom script or a user-supplied song.
Create Talking Photo VideoThree Steps
Select one of the six chips for your ai talking photo: Portrait Says Hello, Family Photo Memory, Pet Owner Chat, Birthday Greeting, Holiday Wishes, or Funny Reaction. Portrait Says Hello is selected by default. Each preset describes a different setting.
Add a clear image of yourself or an adult who has agreed to appear. This page takes one photo and does not support a second reference image, a custom scene prompt, or your own audio track. Check that the face is visible before you continue.
Press Create Talking Photo Video to make a 15-second vertical result. Review the scene and soundtrack before sharing: the video includes environmental sound and instrumental music, but no spoken voice. Add a caption separately if your post needs a written greeting or joke.
Scene 01 · Family Photo Memory
A quiet moment for a family memory.
Family Photo Memory places the person from your image in a warmly lit home, looking toward the camera with a thoughtful expression. Use the scene for a gentle tribute, a family chat, or a personal keepsake. This is an animated interpretation of a still image, not a recording of the person speaking. The soundtrack has environmental sound and instrumental music, with no human voice.
Scene 02 · Pet Owner Chat
The pet joins the frame; the soundtrack stays wordless.
Pet Owner Chat places the pictured person beside a relaxed pet at home, with both visible in a cozy, naturally lit room. Pick it when the joke or memory belongs to the person and their animal together. The clip does not generate dialogue for either of them: its audio contains environmental sound and instrumental music, not speech. Upload a person’s photo and choose this preset scene.
Scene 03 · Birthday Greeting
Balloons, warm lights, and a camera-facing pose.
Birthday Greeting puts the person from your photo in a softly lit birthday setting with a few balloons and warm lights in the background. It gives a birthday post a visual setup without asking the pictured person to deliver a spoken message. Add your own caption when you share the clip if you want to include a greeting. The generated video lasts 15 seconds and has instrumental music and environmental sound.
Scene 04 · Holiday Wishes
A seasonal scene with a quiet, camera-facing pose.
Holiday Wishes places the pictured person beside a warmly glowing decorated tree in a cozy holiday room. Choose it for a seasonal post or a lighthearted message to family. The scene supplies the holiday setting, while the generated soundtrack supplies environmental sound and instrumental music. There is no spoken wish in the video, so add a caption or message separately if you want to send specific words.
Scene 05 · Funny Reaction
Let the expression carry the punchline.
Funny Reaction puts the person at a table in a bright, uncluttered room with a mildly puzzled expression. Use it as a visual reaction when the joke works better as a look than as a line of dialogue. The preset creates the scene from one person’s photo; it does not let you write a custom script or add your own song. The 15-second soundtrack has environmental sound and instrumental music, without human speech.
Straight Answers
The setup for an ai talking photo is deliberately specific: one consenting adult’s photo, a preset scene, and a short video. Here is what you can expect before you upload.
The Trend Explained
An ai talking photo on this page is a short video made from one person’s still image and one selected scene. MiniMax H3 places the person in that setting and returns a 15-second vertical clip with environmental sound and instrumental music. Despite the familiar name, this version does not produce speech: there is no spoken voice, script, or user-uploaded song. The scene choices focus on a family memory, a pet-owner moment, a birthday, a holiday, or a puzzled reaction. This makes the result a visual greeting or joke you can caption yourself, rather than a talking avatar or a voiceover video.
Upload one photo that shows a consenting adult clearly for this ai talking photo. The tool uses that image as the basis for the video and does not accept a second reference photo on this page. A face that is visible and well lit gives the scene a clear subject. Use your own image or get the pictured adult’s permission before making or sharing an animation.
Choose from six scene options: Portrait Says Hello, Family Photo Memory, Pet Owner Chat, Birthday Greeting, Holiday Wishes, or Funny Reaction. Portrait Says Hello is selected by default. Each option sets a distinct location and mood, from a warmly lit home to a table in a bright room. You select from these chips; the tool does not provide a free-text prompt for inventing another setting.
MiniMax H3 returns a 15-second, 9:16 one-photo talking video with environmental sound and instrumental music. It does not make the person speak, and you cannot upload a song or voice recording to replace the soundtrack. If you want the clip to carry a specific greeting, write it in your post caption rather than expecting to hear it in the video.
Straight answers about the photo, scenes, sound, duration, and sharing.
Create Talking Photo VideoChoose one of the scene chips, upload one photo of a consenting adult, and start generation. MiniMax H3 makes a 15-second vertical video with environmental sound and instrumental music. It does not add a spoken line, so write a caption separately if you want the post to include a message.
No, the generated clip has no human voice or dialogue. It includes environmental sound and instrumental music, so it is a visual animation rather than a spoken greeting or voiceover. You can add written words in the caption where you share the result.
No, this tool does not accept a user-supplied song or voice recording. MiniMax H3 creates the soundtrack with environmental sound and instrumental music, without speech. If you need a specific spoken message or track, this preset workflow will not add it to the video.
Use one photo of one person for each video. This page does not provide a second photo slot or a group-photo workflow. Choose an image where the adult’s face is easy to see, and make sure you have permission to use it.
There are six scene choices: Portrait Says Hello, Family Photo Memory, Pet Owner Chat, Birthday Greeting, Holiday Wishes, and Funny Reaction. Portrait Says Hello is the default selection. Each chip sets the location and mood for the result, and the tool does not let you type a new scene.
Each result is 15 seconds long and uses a vertical 9:16 aspect ratio. That format suits a short post or message, while the fixed duration keeps the scene brief. The video includes environmental sound and instrumental music but no spoken voice.
This page makes a short talking portrait video from a selected preset, not a custom talking-head performance. You cannot enter a script, upload a voice recording, or choose your own song here. Pick one of the five scenes and use a caption for any words you want to accompany the clip.
Use a photo only when the pictured adult has agreed to appear. The tool turns that person’s still image into an animated video, so permission matters before you generate or share the result. Do not upload an image of someone who has not consented.
Read the guide to making an AI trend video for a general walkthrough of choosing a concept and preparing a post. For this ai talking photo, the specific workflow is one consenting adult’s image, one preset scene, and a 15-second vertical result without speech; it creates a photo that talks only visually.
Explore More
Wordless Scene
Create an ai talking photo from one consenting adult’s image, choose a preset, and get a 15-second vertical clip with instrumental music and no spoken voice.
Create Talking Photo VideoOne photo • 15 seconds • 9:16 vertical
Give One Portrait a
Create Talking Photo Video