Feature updates⚡️

Minor updates but they are necessary for creating apps.

• Make it possible to set role to the next message after function calling #247
• Add support for muting microphone #248
• Add character message window #249
• Support favoring specific phrases on Google Text-to-Speech #250

Unagirl, a new demo character debuts🥰

• Unagirl debuts as a new demo character🥰 #255

See Unagirl in dress at vroid hub https://hub.vroid.com/characters/7204218679890800631/models/6961078537805052952

Other updates and fixes🐈

• Improve HTTP error debugging #251
• Use UniTask in HTTP request #252
• Fix VoiceRecorder fails in starting #253
• Fix warning message when no skill router is attached #254

Full Changelog: v0.6.2...v0.6.3

🥳Create ChatGPT-based AI assistant smarter

ChatGPT is no longer just one of the various skills but is integrated as a conversation processing system of ChatdollKit.

• Add autonomous routing system by ChatGPT⚡️ #241

You can add skills much smarter: All you have to do is making the definitions of the interface of ChatGPT function calling and to implement the logic to handle the result from the function.

See also the example.
https://github.com/uezo/ChatdollKit/blob/master/Examples/ChatGPT/FunctionSkills/WeatherSkill.cs

🌎 Better experience on WebGL

• Support ChatGPT stream mode in WebGL #244

👍 Other updates

• Add support for ChatGPT function calling #239
• Support starting conversation without prompt #243
• Fix bug that ChatGPT func is not registered #245
• Fix performing response bugs #246

Full Changelog: v0.6.1...v0.6.2

⚡️ Improve performance, stability and developer experience

• Make GetDialogToken public #225
• Improve message window #226
• Add example of using ChatGPT in streaming mode #227
• Start idling when no animations on start #230 #231
• Avoid errors when setting unregistered face expressions #232 #233
• Add missing inheritance to SkillRouterBase #234
• Make compatible easily with the latest VOICEVOX #235
• Improve ChatGPT response speed🚅 #236
• Update demo for v0.6.1 #237

🐞 Fix bug

• Fix bug that iOS build fails #218
• Fix bug that voice cache doesn't work #224

Full Changelog: v0.6...v0.6.1

❤️ Emotion Simulation powered by ChatGPT

Add ChatGPTEmotionSkill as an out-of-the-box example that express the emotion as face expressions while conversation.
Also add sample motions while thinking (waiting response from ChatGPT) and support multiple idle animations (change pose periodically).
You can build rich 3D AI virtual assistant lightning fast⚡️

• Add example of ChatGPT with emotion engine by @uezo in #209
• Support multiple idle animations by @uezo in #214

💡 Improve prompt engineering interface

Support one-shot prompt: system message content and a pair of user and assistant message content as an example turn. You can configure it on inspector, and even runtime for they are the public fields.

• Support prompt engineering for ChatGPT by @uezo in #207
• Easy to customize chatgptskill by @uezo in #208

🚅 Support runtime VRM loading

Support configuration at runtime. This enables you to build apps that uses user own VRM.

• Support runtime VRM loading by @uezo in #205

⚡️ Improve performance and stability

Improve FPS about 30% on my machine and stability of controlling animation gets better. They are basically internal refactoring but that includes some destructive changes.

• Use animator parameters to set animation instead of state name.

// ~ v0.5.3
response.AddAnimation("AnimationName");

// v0.6
response.AddAnimation("BaseParam", 6);

• PreGap and PostGap no longer available for the argument of Animation and FaceExpression. Use duration to adjust timing.

• Improve animation performance⚡️ by @uezo in #210
• Make FaceExpression feature runs in Update() by @uezo in #211
• Simplify the interface to control model by @uezo in #212

Other changes

• Add Azure OpenAI's ChatGPT Skill by @nakazax in #202
• Use uLipSync as the default LipSync library by @uezo in #203
• Change Azure Text-to-Speech default voice by @uezo in #204
• Make it possible to observe the status of dialog by @uezo in #206
• Fix build error in uLipSyncHelper by @uezo in #213
• Messagebox in hierarchy by @uezo in #215
• Make FaceClipConfiguration create various expressions by @uezo in #216

New Contributors

• @nakazax made their first contribution in #202

Full Changelog: v0.5.3...v0.6

ChatGPT support✨

Skill for contextual conversation with ChatGPT and it's demo is included!
You can develop and start talking 3D model based virtual agent lightning fast⚡️

• Add ChatGPT ready example and demo #198

Add UI components😊

Add slider for microphone volume and FPS indicator.

• Add UI Components (Mic volume and FPS) #199

Others

Fix some bugs for WebGL platform.

• Fix some build errors #197

Separate ChatdollKit components from avatar object

Separate ChatdollKit components from avatar object to manage components easier; setting up, changing 3D model or something like that use cases. At this version, the developer can complete configuration by just adding ChatdollKit prefab to the hierarchy and configuring some components attached to this prefab. #190

Support uLipSync configuration

To set up uLipSync select uLipSync on the inspector of ModelController and then start Setup ModelController. #191

Demo

• Add a skill using GPT3 based chatting API by OpenAI. #193
• Out-of-the-Box demo for Oculus VR. Enjoy chat with the ChatdollKit demo girl in VR. #195

This update includes small/internal changes, bugfixes and Watson Assisntant support.

• Add support for implementing prompter in RequestProcessor #182
• Add support for Watson Assistant #184
• Fix bug sending ping to remote dialog server before URL is set #183
• Fix index error in Watson TTSLoader #185

Support server side dialog management

• Devide request processing from conversation loop #169

Improve editor

• Switch speech services and request processor on editor #177
• Make it possible to send text to WakeWordListener instead of voice #170
• Move dialog configurations to DialogController #171

Other updates

• Fix bug for updating face clip fails #168
• Make constructors of Request and Response to take more arguments #172
• Change file structure

🌐 WebGL support 🎉

Now you can create virtual assistants that runs on web browsers!

• Use UniTask instead of C# standard Task for async/await #156
• Add support for microphone on WebGL🎤 #157
• Text-to-Speech on WebGL #158
• Add support for Watson Text-to-Speech on WebGL #159
• Add MemoryUserStore #166

Add new super kawaii voices to VOICEVOX

• Add speakers to Voicevox TTS Loader #165

Female

• Metan Shikoku: Sweet / Normal / Tsun / Sexy
• Zundamon: Sweet / Normal / Tsun / Sexy
• Tsumugi Kasukabe
• Hau Amehare
• Ritsu Namine
• Himari Meimei

Male

• Takehiro Kurono
• Kotaro Shirakami
• Ryusei Aoyama

Other updates

• Make it possible to indicate voice detecting status #160
• Allow skill server to update topic name #161
• Make the size of SimpleMessageWindow relative #164

VOICEVOX support

VOICEVOX is a super ❤️kawaii❤️ Text-to-Speech application by Hiroshiba-san.

• Support VOICEVOX as a Text-to-Speech engine😍 #146
• Make Shikoku Metan speak slowly #150

Demo and improvements for developers

We provide the demo that runs without any API keys. Perfectly OOTB.👍 This demo uses VOICEVOX server and Chat server hosted by ChatdollKit project. Please don't use these services for production and follow the rules VOICEVOX project provides. (See the bottom of README)

• Make CancelWord set from application config to VoiceRequestProvider #148
• Enable to send request by text instead of voice on inspector #149
• Add simple chat example that doesn't require API key #151
• Bring the control buttons top of inspector #152
• Fix bug that Stop chat button doesn't work when listening voice req #153
• Add demo that runs out-of-the-box #154

Others

• Simplify internal application configuration #145
• Change default format of AzureTTS from WAV to MPEG #147
• Include unity meta files

Full Changelog: v0.3.2...v0.3.4