Hi everyone,
we’ve released PhonemeX Pro, a modular speech and character animation system for Unity, and we’re now working on the next update.
The current version already includes offline on-device TTS, real-time phoneme timing, lip sync, avatar driving, blendshape/custom driver support, and a face rig + expression system for emotions and micro-expressions.
The bigger direction is to bring everything related to character speech into one modular system. So instead of having separate tools for speech generation, phoneme data, lip sync, avatar animation, and later AI interaction, we want PhonemeX to become one connected pipeline for Unity characters.
We’re currently preparing new subsystems in the same direction, including ASR and LLM-related modules, but before locking the next feature list, we wanted to hear from Unity developers who are working with NPCs, avatars, digital humans, visual novels, educational characters, or interactive simulations.
What would you want from a system like this?
Asset page:
There are Windows and macOS demo builds on the page if anyone wants to test the current runtime behavior.
We’d really like to hear what people need before we finalize the next update priorities.