Recently, AI artificial intelligence tools are developing rapidly. ChatGPT chatbots, Midjourney AI drawing tools, etc., can quickly solve human daily life problems online. If you want to move the original static photos of people to speak, you can use DID online photos AI virtual reality video technology can also be quickly implemented.
DID online production can make portrait photos speak, mainly using the latest AI combined with real-life video technology to make portraits orPhotos of loved ones movecan also replacephoto plus audioOr script content, combine portrait photos and voices, and the characters will automatically speak. This service supports Chinese and English voices, it is quite powerful and easy to use.
DID Free one-click generation of photos of people and moving videos
D-ID is a company that provides services and development of AI-like live-action video products. Just upload a portrait photo and input the content to be said, and the AI voice robot can automatically convert it into audio, and even upload the recording file, and you can quickly Get a very realistic opening composite movie. These can be used in scenarios such as photos of loved ones, virtual lecturers, hosts, AI robots, or special effects for movies, and are very suitable for educational or various service occasions.
Let me share below how to use DID to create talking character photos online, and use the most popular ChatGPT chat robot and Midjourney AI drawing tool. If you want to synthesize portrait photos and voices, you can first look at the final example results below. This is Through a plane photo generated by AI drawing, and with the video synthesized by AI voice, you will find that the mouth in the picture will automatically move according to the voice, and there will be some movements on the face, such as blinking, smiling, shaking the head, etc. , looks just like a real person.
How to use DID to make portrait photos speak
First, open the web page of moving photos and dubbing online on DID, and click on the upper right corner “FREE TRIAL” to start a free trial.
After entering the Video Library screen, click the “CREATE VIDEO‘ to start creating a new composite video.
Set national language and AI voice
In the AI composite photo editing screen, first set the Chinese voice, select the country language from the right, if Taiwan, look for “Chinese（Taiwanese）“, but at present there are relatively few choices of traditional Chinese AI voice and tone. If you want more diversified voices, you can change to Simplified Chinese language, and you can see more diverse voices and age groups.
Under Voices, you can choose male or female AI voices. For example, there are currently only three choices for traditional Chinese voices.
Select or add a portrait photo
can come againCustom Portrait Photosdifferent character templates will be provided by default. If you want to customize the photo, you can click “ADD“buttonUpload a portraitwhen uploading photos, pay attention to the following points:
- The person should be in the center of the photo, and the head should not be cut in half
- Facing fully forward with no teeth showing
- The minimum image resolution needs to be 200×200 pixels
- The light in the photo is stable, not dark or blurry
- Upload photos can only be up to 10MB
When uploading, you need to join the DID member account prompt, you can directly use Google or Email to register for free.
If you don’t know which photos are available, we recommend using the following two types of portrait material pictures generated by AI drawing:
Enter text content and upload audio files
next, toSet Speech Transcript Sectionyou can enter the content you want to type, orDirectly use the ChatGPT chat robot to quickly generateFor example, if you want to make a self-introduction video, you can ask the AI robot to introduce yourself to explain your current work and interests.
at lastPaste the text in the Script boxclick belowhorn buttonconfirm whether the AI voice is what you want, if you don’t like it, you can adjust the voice through Voices,Clock button to adjust speech speed,ifwant to upload recording fileYou can also, just click “Audio“After uploading the recording file, the photo and voice can be synthesized through the DID platform.
Custom Composite Video Title
Finally click the upper left cornerCustom Composite Video Titleyou can directly input both Chinese and English, mainly for the convenience of identifying the project name when you want to continue to generate other AI portrait voice videos.
Output talking photo character video
Finally, click on the upper right corner “GENERATE VIDEO” to start exporting video files.
5 credits will be consumed for each video output, and 20 credits can be used for free after account registrationwhich means that each group of accounts can output 4 times for free. After the photo and voice text are confirmed, click “GENERATE“Start transcoding output.
Download DID People Video
After a period of time, after the synthesis is completed, you will see thumbnails of the character images displayed in the Video Library, and you can directly click on them if you want to download and watch the finished product.
You can click on the video to start playing, and you will see that the characters in the photo start to move. At the same time, there will be different expressions, mouth shapes and swaying movements according to the voice. Just click “DOWNLOAD” to download the video.
function summary
DID is a very convenient and free online synthesis virtual reality video platform, which can make a seemingly ordinary photo, synthesize voice and sound through AI technology, and quickly complete a very realistic character talking video, currently free The version can output videos up to 4 times. If it exceeds, you need to pay to unlock and remove the watermark. If you need it, you can experience the output for free first. If you feel practical and need a lot of use, you can pay.
More practical AI technology tools and teaching recommendations: