D-id can create AI models from an image or a prompt and can then generate lip synced videos.
Replicate hosts a lot of the best open sourced AI services. It has loads of Stable Diffusion models which can generate images of people. You can then use one of the text to speech tools to create the audio (Bark is my favourite) and Sadtalker to make videos from the images.
D-id is a monthly subscription, Replicate allows you to pay as you go per minute of runtime for the AI service.
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.