I am working on a completely automated, AI-driven MetaHuman workflow.
As a developer, I got great results, but I need some help to finish the workflow and get input from content creators where else we can help with automation.
I am looking to cooperate with MetaHuman Experts in exchange of Text to Speech → Lip Sync service (50% off for a year) or some other mutually beneficial compensation, strengthening a possible symbiotic relationship.
The service description
-
English text (or Speech Synthesis Markup Language SSML) is translated to any of the 130+ languages.
-
If SSML is used instead of text, certain segments of the text (SSML) can be pronounced in different languages and meta markers can signal animation with parameters.
-
Based on voice selection (many hundreds of male, female, and child voices) an MP3 audio is generated.
-
The Speech Marks (viseme, word, sentence timing) file is generated.
-
iClone plugin (written by me) takes the audio and Speech Marks input and provides Lip Synced audio for a model.
Examples: