v0.8.4

🧩 Modularized for Better Reusability and Maintainability

We’ve reorganized key components, focusing on modularity to improve customizability and reusability. Check out the demos for more details!

• Add modular demos #381
• Support getting and clearing LLM context through DialogProcessor #383
• Introduce LLMServiceExtensions for Centralized Custom Processing #382

🧹 Removed Legacy Components

Outdated components have been removed, simplifying the toolkit and ensuring compatibility with the latest features. Refer to 🔄 Migration from 0.7.x if you're updating from v0.7.x.

• Remove legacy v0.7.x components #376

🍩 Other Updates

• Set default StopChat behavior to skip user input prompt #377
• Fix LLMService IsEnabled handling #379
• Unify speech handling regardless of source in ModelController #380

Full Changelog: 0.8.3...0.8.4

v0.8.3

✨ New features

• Add SpeechListener for Azure Speech SDK stream mode #361
• Add functionality to interrupt character speech #367
• Add pause functionality to insert delays in character speech #368

💃 Easier Animation Registration

• Add named animation registration #360
• Make it easier to register animations #366

🍩 Other updates and bug fixes

• Migrate to LLMService Context Management #362
• Fix bug where SpeechListener doesn't listen after error #364 #365
• Add auto start functionality to AzureStreamSpeechListener #369
• Add support for OpenAI TTS on WebGL #370
• Fix bug where Function Calling fails #372
• Fix Gemini fails after function calling #371 #373
• Update demo for v0.8.3 #374

Full Changelog: 0.8.2...0.8.3

v0.8.2

🌐 Control WebGL Character from JavaScript

We’ve added the ability to control the ChatdollKit Unity application from JavaScript when running in WebGL builds. This allows for more seamless interactions between the Unity app and web-based systems.

• Enable WebGL interaction via external JavaScript #355

🗣️ Speech Synthesizer

A new SpeechSynthesizer component has been introduced to streamline text-to-speech (TTS) operations. This component is reusable across projects without Model package, simplifying maintenance and reusability.

• Add SpeechSynthesizer as new mainstream TTS component #354
• Speech synthesizer updates #358
• Improve TTS handling for empty strings and errors #353

🍩 Other Updates

• Small changes for v0.8.2 #356
• Update demo v0.8.2 #357
• Prevent user request from being overwritten by noise #359

Full Changelog: 0.8.1...0.8.2

v0.8.1

🏷️ User-Defined Tags

You can now include custom tags in AI responses, enabling dynamic actions. For instance, embed language codes in replies to switch between multiple languages on the fly during conversations.

• Add support for user-defined tags in response messages #342
• Add support for user-defined tags (Claude, Gemini and Dify) #350

🌐 External Control via Socket

Now supports external commands through Socket communication. Direct conversation flow, trigger specific phrases, or control expressions and gestures, unlocking new use cases like AI Vtubers and remote customer service.

• Add SocketServer to enable external request handling via socket communication #345
• Add DialogPriorityManager for handling prioritized dialog requests #346
• Add option to hide user message window #347
• Add ModelRequestBroker for simplified model control via tagged text #348

Check out the client-side demo here: https://gist.github.com/uezo/9e56a828bb5ea0387f90cc07f82b4c15

🍩 Other Updates

• Fix bug where expressions on error doesn't work #344
• Improve text splitting logic in SplitString method #349
• Update demo for v0.8.1 #351

Full Changelog: 0.8.0...0.8.1

v0.8.0

💎 What's New in Version 0.8 Beta

To run the demo for version 0.8.0 beta, please follow the steps below after importing the dependencies:

• Open scene Demo/Demo08.
• Select AIAvatarVRM object in scene.
• Set OpenAI API key to following components on inspector:
  • ChatGPTService
  • OpenAITTSLoader
  • OpenAISpeechListener
• Run on Unity Editor.
• Say "こんにちは" or word longer than 3 characters.
• Enjoy👍

⚡ Optimized AI Dialog Processing

We've boosted response speed with parallel processing and made it easier for you to customize behavior with your own code. Enjoy faster, more flexible AI conversations!

• Optimize AI-driven interactions by @uezo in #335

🥰 Emotionally Rich Speech

Adjusts vocal tone dynamically to match the conversation, delivering more engaging and natural interactions.

• Improve expressiveness of text-to-speech output by @uezo in #336
• Allow adding emotion to speech synthesis by @uezo in #337

🎤 Enhanced Microphone Control

Microphone control is now more flexible than ever! Easily start/stop devices, mute/unmute, and adjust voice recognition thresholds independently.

• Add new SpeechListener namespace with voice input modules by @uezo in #334

🍩 Other Changes

• Fix some bugs in StyleBertVITSTTSLoader by @uezo in #333
• Update for v0.8.0 beta by @uezo in #338

Full Changelog: 0.7.7...0.8.0

v0.7.7

🥰 Support StyleBertVits2

We've added support for Text-to-Speech using the StyleBertVits2 API! 🎙️✨ Now, your AI characters can speak with even more expressive and dynamic voices, making them shine brighter than ever! 😎 Get ready to take your character's charm to the next level! 🚀💫

• Support StyleBertVits2 API as TTS service by @uezo in #327

💕 Support Cohere Command R 💕

• Add experimental support for Command R by @uezo in #329
• Add experimental support for Command R on WebGL by @uezo in #331

🐸 Other Changes

• Fix bug in handling response when using Azure OpenAI by @uezo in #325
• Add option to completely disable WakeWordListener by @uezo in #326
• Fix bug causing ToolCalls to fail by @uezo in #328
• Provide workaround to clear state data, including LLM context by @uezo in #330
• Update WebGLMicrophone.jslib by @uezo in #332

Full Changelog: 0.7.6...v0.7.7

v0.7.6

What's Changed

🎓LLM related updates

• Add support for Dify Agents by @uezo in #315
• Add support for custom logic at the end of LLM streaming by @uezo in #316
• Internalize Dify ConversationId in state data by @uezo in #318
• Use GPT-4o mini as the default model for ChatGPT by @uezo in #321

🗣️ Dialog control

• Fix WebGL microphone input handling by @uezo in #317
• Improve WakewordListener functionality and debugging by @uezo in #320

🥰 3D model control

• Enable runtime loading of VRM models from URL and byte data by @uezo in #322

🐈 Others

• Update demo v0.7.6 by @uezo in #323

Full Changelog: 0.7.5...0.7.6

v0.7.5

Dify Support 💙

• Add support for Dify💙 by @uezo in #309
• Add support for Dify TTS and STT by @uezo in #311

Other changes

• Fix bug where mic volume changes are not applied immediately by @uezo in #307
• Enhance camera functionality with manual still capture and sub-camera switching by @uezo in #308

Full Changelog: 0.7.4...0.7.5

v0.7.4

👀 Enhanced Vision Capabilities

This update introduces autonomous vision input for Gemini and Claude, and adds vision input support for WebGL. Now, various AIs can offer richer conversational experiences with integrated vision input across different platforms.

• Support autonomous vision input for Gemini✨ #302
• Refactor Vision input and various related improvements #303
• Support autonomous vision input for Claude✹ #304
• Add vision input support for WebGL #305

Full Changelog: 0.7.3...0.7.4

v0.7.3

👀 Support dynamic vision input for ChatGPT

By adding a SimpleCamera to the scene and including [vision:camera] in the response message, the system will autonomously capture images when visual input is required for a response.

• Add autonomous image input handling for ChatGPT #298

📦 Easy setup by modularized UI components

Microphone volume sliders and request input forms have been modularized. These can now be used immediately by simply adding the prefabs to the scene without any additional setup.

• Modularize UI components for easy scene addition in #300

🎙️ dB-based microphone volume

• Change volume measurement from amplitude to decibels #296
• Fix incorrect volume measurement bug #299

✨ Other changes

• Switch from function call to tool call for ChatGPT Function Calling #297
• Remove deprecated ChatGPT-related modules in #301

Full Changelog: v0.7.2...0.7.3