TTS lipsync through Audio2face to Metahuman in realtime

Hi, is currently any solution to load a text, TTS, generate a wav and play the metahuman reading the text with lipsync in real time in Unreal?

What would be the pipeline?

What are closest solutions as of today?

1 Like

Currently the audio input only supports pre-recorded files but in future Nvidia plans to support live audio source input from microphones.

Hi @xabierolaz, welcome to Audio2Face.
We will be releasing a new version very soon which supports TTS streaming into Audio2Face.
Regarding the real-time animation play on metahuman, we don’t support it yet. The closest solution is exporting the blendshape animation (using blendshape conversion) and load it into a Metahuman in Unreal.

Hi, any news on this topic?

We’re about to ship a new version now. :) Aiming the end of this week.

1 Like

Hi, is this version released, don’t see any updates. Latest available build is 2021.3.1

Thanks yseol!

@xabierolaz Audio2Face 2021.3.2 is on the launcher now. :)

1 Like

I am really happy to get AudioStreaming feature out of a2f. But I wonder if I can get the output of a2f in a form of any API, so that I can use it in my python program. I saw somewhere a2f will be a part of NVIDIA Maxine SDK. I would like to know if it is the case.