Skip to content

v2.0.0

Latest
Latest

Choose a tag to compare

View all tags
@HardCodeDev777 HardCodeDev777 released this 12 Oct 15:45
· 1 commit to main since this release
v2.0.0
c35db38
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

🎉 Finally... UnityNeuroSpeech v2.0.0!

There are a lot of changes — but I’ll only mention the ones that really matter:
 

TTS

  • No more Python! No more local servers! No more pain! UnityNeuroSpeech now uses the amazing and actively maintained Coqui XTTS fork by Idiap — and everything runs directly through the CLI. Yes, you’ll need to install UV, but it’s so much better than before.

Unity

  • Added full support for multiple voices, languages, and agents
  • Added dialog history saving (with or without AES encryption) between player and LLM
  • Whisper models now work from StreamingAssets/, meaning full Mono support. Unfortunately, IL2CPP currently not supported. I'm planning to add support for it in v2.1.0.
  • Removed AgentState struct and added SetJsonDialogHistory method
  • Added two powerful new Editor tools: Prompts Test and Decode Encoded
  • Improved code comments, logs, and internal validation

Docs

  • Simplified and cleaned up documentation — removed duplicate info already shown in Unity tooltips

Setup

  • One beautiful setup.bat file handles everything — it installs all required dependencies automatically 😎 No more 3 ZIPs or manual setup — just a .unitypackage and one script to run.

This version of UnityNeuroSpeech is ready for real, production-level games.
I spent a lot of time testing it — but let’s still hope there are no bugs! 🤠

Assets 3
Loading