To make character in the image look like talking, we can utilize artificial intelligence provided by some websites. I have created a video from an image with a duration of less than 30 seconds. And I have also prepared the audio.
First step, run the browser app. And then go to the lalamu.studio page. After that, select Let's Start. On this page, we can choose the sample audio. To create text to speech, select Add new Audio. You can type in a sentence and choose the voice character that has been provided.
But since I have created the audio before, then I just need to upload it to this site. The audio file to be uploaded must be in MP3 format with a maximum of 5 megabytes, and the duration is less than 30 seconds. After the audio is successfully uploaded, we can also choose the characters that have been provided.
But in this tutorial, I will upload a video that I have created from an image. And now the video has been successfully uploaded. Make sure the audio and video are selected. And then select Generate Lip Sync Video. Wait until the processing stage is complete.
If it has been successfully created, we can preview the video first. To save it, right-click. Choose Save video as. And the result will be like this. Thank you for watching. And see you in another tutorial.
Music: by El Secreto - Yung Logos:
For business inquiries: [email protected]