Please check following points :
1. In the input, we will pass .glb file of avatar and .mp3 file of audio. I have attached sample .glb file of avatar and .mp3 file of audio.
2. In the output, we want a video file where avatar from that glb file is speaking words/sentences from audio file.
3. Make sure that lip sync should happen properly with respect to word.
4. If you want then you can use unreal engine or unity. But video file should have to be generated automatically, because we will use automation script as an API where will pass .glb file of avatar and .mp3 file of audio in the input.
1 freelancer está oferecendo em média ₹25000 para esse trabalho
Hi, I already do Lipsync automation, can help with your project. need time around 2-3day. Contact me in chat to discuss more and I sent you my preview work.