Release Highlights

Add Configuration feature✨

• Load configuration from Resources automatically if config exists
• Save configuration by Inspector of Main Application (Subclass of ChatdollApplication)
• Implement OnComponentsReady to apply configuration to your app
• Implement CreateConfig to save your application settings to config file
• The configuration file name is same as the value of ApplicationName of Main Application. If empty, the name of game object
• See MultiSkills examples to learn more about this feature

Update Demo and Examples🙌

• Change demo 3D model to Tsukuyomi-chan. Thank you so much Yumesaki-san!
  • https://tyc.rei-yumesaki.net
  • https://twitter.com/TYC_Project
• You can run demo application out-of-the-box. Just set API keys for Azure/Google/Watson speech services.
• Add Camera and QRCode reader skills to MultiSkills example and demo.
  • Say "写真を撮って" or "QRコードを読み取って" to use these skills.
  • Import ZXing and uncomment some lines in Examples/MultiSkills/Scripts/QRCodeDecoder to use QR Code reader.
  • ZXing: https://github.com/micjahn/ZXing.Net/releases

Other updates

• Some internal refactoring.
• Bug fix: Preview after taking photo doesn't end e0e6136

Model

• Fix bug Web/TTSVoiceLoader caches even when request timeouts

Conversation

• Enable to check whether the topic is available or not
• Enable to get the list of server-side skills and configure HttpSkillClients for them on application starts

Others

• Add Out-Of-Box Demo
• Add editor menu to remove all ChatdollKit components
• Update and change structure of examples

0.3.0 features available🎉 #143

• Ignore case of WakeWord and CancelWord #140
• Create and update documents #141
  • Create user manual
  • Update README (Added video)

Visit https://uezo.booth.pm/items/2619190 to download unity packages.
Unity Packageは https://uezo.booth.pm/items/2619190 からダウンロードしてください。

Version 0.2.0 provides you application base classes to create custom app super easily🚀

You can start creating virtual assistant application without coding. Of course you can create rich application by extending application base classes and code as you like.

We provide these application bases:

• ChatdollApplication: Application that doesn't depend on any specific cloud services
• AzureApplication: Using Azure Speech Services
• GoogleApplication: Using Google Cloud Speech Services
• GateboxApplication: Base for creating Gatebox application. This depends on GateboxSDK so we provide this as a seperated package.

Model

• Use 3D model name for animator controller as default #131
• Support Google Text to Speech Service #134

Dialog

• Enabled to include request message in wakeword (inline request) #122
• Enable to configure WakeWord on inspector of Application base class #128

Others

• Enable to switch microphone #121
• Make it easier to use MessageWindow and ChatdollCamera #129
• Add vender name to namespace of extensions #139
• Update examples #139

Model

• Enable to change face expression while idling #101 #103
• Enable to change face expression gradually (cross fade) #109
• Add Description property to Voice #112
• Make it strict the timeout of downloading voice #113
• Refactor and improve ModelController #114

Dialog

• Enable to customize the first step of conversation #102 #104
• Enable to apply updated user info on server #105
• Make it easier to add animations, voices and faces to response of dialog #107
• Enable to handle error status from external components #108

Others

• Stop voice recorder after getting recorded voice #106
• Add methods for debug to ActionHistoryRecorder #111

Model

• Reset viseme after speech #93
• Change face clip configuration from JSON to Asset #99

Dialog

• Enable to stop conversation while downloading Web/TTS voice #98
• Add HttpPrompter #100 See also server side SDK for Python 👉 https://github.com/uezo/chatdollkit-server-python

Others

• Enable to raise wakeword detection threshold when chatting #95
• Set false to AudioSource.playOnAwake #96
• Enable to cancel HTTP request #97

Dialog

• Add PreProcessor method to DialogProcessor #84
• Enable to update context data at server side ExtractIntent #85

Model

• Enable to prefetch and cache TTS/Web voice by default #86
• Change path to face configuration file to relative path #91

Others

• Avoid to recognize too long phrase for wakeword #90

Dialog

• Move ExtractIntentAsync from IntentExtractor to DialogRouter #75
• Move showing waiting animation from DialogRouter to DialogProcessor #80
• Add waiting animation function to HttpDialogProcessor
• Change interface of IDialogRouter

Model

• Set BlinkBlendShapeName automatically #76
• Trim the name of ShapeKey before evaluating whether it is a key for viseme #77
• Move setting Web/TTS voice loaders to ModelController #78
• Set default to Text-to-Speech loaders #81

Others

• Start WakeWordListener without implementing OnWakeAsync #79

• Enable to configure default settings on inspector of VoiceroidTTS #70
• Add support loading face clips from file automatically #71
• Improve usage of WakeWordListener #72
• Enable to cancel ChatdollCamera and RequestProviders using camera #73
• Enable to play AnimatedSay from JSON #74