Audio-driven Talking Face Video like Synthesia or synthesys.io
Budget: $800 – $1,200 USD
I want to get a project done in python that does what those projects do. They are using text to create an audio and using those audio to drive the lips of the video. There are many repos like that on Github that can help you to get started. I have tested them all.
Note: You do not have to make a full web interface like you see in the examples I mentioned. Only the python part that can create lip synced videos from audio.
Note: I have used Wav2Lip and it is not suitable. Since we need it to work on video.
Note: You do not have to make a full web interface like you see in the examples I mentioned. Only the python part that can create lip synced videos from audio.
Note: I have used Wav2Lip and it is not suitable. Since we need it to work on video.