I2V - Talking Avatar workflow
Hello, I have a question about the I2V - Talking Avatar workflow.
I dont understand how the uploading audio works. I thought that by uploading it the provided image will be synced with the audio?
Everytime I use it I have to write something in the Prompt (what to say) textbox and that seems to be overwritting it?
I tried it out today and got some results, but that part confused me the most.
Yes this is a voice clone. Meaning you type what to say, and it uses the voice from the provided audio file to create a new speech.
If you just want lip-sync and use the speech included in the audio file as is, you want to use the Custom Audio workflows:
T2I: https://huggingface.co/RuneXX/LTX-2-Workflows/blob/main/LTX-2%20-%20T2V%20Basic%20(custom%20audio).json
I2I : https://huggingface.co/RuneXX/LTX-2-Workflows/blob/main/LTX-2%20-%20I2V%20Basic%20(custom%20audio).json