Make your Unity characters hear, think, and talk — using real voice AI. Locally. No cloud.
UnityNeuroSpeech is a lightweight and open-source framework for creating fully voice-interactive AI agents inside Unity.
It connects:
- 🧠 Whisper (STT) – converts your speech into text
- 💬 Ollama (LLM) – generates smart responses
- 🗣️ XTTS (TTS) – speaks back with custom voice + emotions
All locally. All offline.
No subscriptions, no accounts, no OpenAI API keys.
- 🎮 AI characters that understand your voice and reply in real time
- 🗿 NPCs with personality and memory
- 🧪 Experiments in AI conversation and narrative design
- 🕹️ Voice-driven gameplay mechanics
- 🤖 Interactive bots with humanlike voice responses
| Feature | Description |
|---|---|
| 🎙️ Voice Input | Uses whisper.unity for accurate speech-to-text |
| 🧠 AI Brain (LLM) | Easily connect to any local model via Ollama |
| 🗣️ Custom TTS | Supports any voice with Coqui XTTS |
| 😄 Emotions | Emotion tags (<happy>, <sad>, etc.) parsed automatically from LLM |
| 🎛️ Agent API | Subscribe to events like BeforeTTS() or access AgentState directly |
| 🛠️ Editor Tools | Create, manage and customize agents inside Unity Editor |
| 🧱 No cloud | All models and voice run locally on your machine |
| 🌐 Multilingual | Works with over 15+ languages, including English, Russian, Chinese, etc. |
- 🧠
Microsoft.Extensions.AI(Ollama) - 🎤
whisper.unity - 🐍 Python Flask server (for TTS)
- 🧊 Coqui XTTS model
- 🤖 Unity 6
See UnityNeuroSpeech official website.
UnityNeuroSpeech was created by HardCodeDev —
indie dev from Russia who just wanted to make AI talk in Unity.
UnityNeuroSpeech is licensed under the MIT License. For other Licenses, see Licenses.