Requires the Dialogue System for Unity (2.2.46+).

>> Manual | Video Tutorials

>> Runtime Conversation Demo

Supports:

• GPT-4o, GPT-4o-mini, GPT-4.5 Preview, and all other OpenAI language models.
• Llama 3.2 & Llama 3.3 models using Ollama.
• DALL-E for images
• Whisper for speech recognition
• ElevenLabs, OpenAI, Overtone, or DeepVoice AI for speech synthesis.

Use generative AI to write narrative content faster, get suggestions when you’re stuck, fix spelling and grammar, and translate your text to other languages. You can also use the addon for freeform chat similar to ChatGPT -- ask for quest ideas, get help writing code, and more. The addon is fully integrated into the Dialogue System for Unity's Dialogue Editor for a friction-free experience that's easy to use for beginners yet powerful enough for expert content creators. It uses your own OpenAI API key (pricing) to create and update dialogue content at edit time. Or you can use Ollama to run Llama 3.2 and Llama 3.3 models locally on your machine.

Supports optional runtime use to generate dialogue on the fly, in response to the user's freeform text input and/or game state, and get information back into your game state based on the end result of the conversation. However, you can also use it solely in the Unity editor at design time if you prefer so you won't accrue any OpenAI API costs during play.

• Generate conversation using your characters and topics - including at runtime
• Generate NPC barks
• Revise text -- spruce up your dialogue, fix spelling & grammar, add variations
• Translate dialogue and quests to other languages
• Freeform chat with GPT-4o/Turbo/GPT3_5_Turbo for a ChatGPT-like experience
• Supports your own fine-tuned models
• Generate actor portrait images using DALL-E
• Use Whisper for speech-to-text recognition
• Generate voiceover audio using OpenAI, ElevenLabs, Overtone, or DeepVoice AI. (To use Overtone or DeepVoice integration, you must have a separate license for them. This addon provides an integration; it does not include Overtone or DeepVoice.)

Note: This addon uses the OpenAI API, so if you're using the OpenAI features you must be able to access api.openai.com from your geographic region. If you're using Llama, you don't need access to the OpenAI API.

No scripting required. Includes complete, documented source code.