Repository files navigation

3D virtual assistant SDK that enables you to make your 3D model into a voice-enabled chatbot.🇯🇵日本語のREADMEはこちら

• 🐈 Live demo A WebGL demo. Say "Hello" to start conversation. She’s multilingual, so you can ask her something like "Let's talk in Japanese" when you want to switch languages.
• 🍎 iOS App: OshaberiAI A Virtual Agent App made with ChatdollKit: a perfect fusion of character creation by AI prompt engineering, customizable 3D VRM models, and your favorite voices by VOICEVOX.

• Generative AI Native: Supports multiple LLMs like ChatGPT, Anthropic Claude, Google Gemini Pro, Dify, and others, with function calling (ChatGPT/Gemini) and multimodal capabilities.
• 3D model expression: Synchronizes speech and motion, controls facial expressions and animations autonomously, supports blinking and lip-sync.
• Dialog control: Integrates Speech-to-Text and Text-to-Speech (OpenAI, Azure, Google, VOICEVOX / AivisSpeech, Style-Bert-VITS2, NijiVoice etc.), manages dialog state (context), extracts intents and routes topics, supports wakeword detection.
• Multi platforms: Compatible with Windows, Mac, Linux, iOS, Android, and other Unity-supported platforms, including VR, AR, and WebGL.

• 🥳 Silero VAD Support: ML-based voice-activity detection vastly improves turn-end accuracy in noisy settings, enabling smooth conversations outdoors or at events.
• 🪄 TTS Pre-processing: Optional text pre-processing lets you fine-tune pronunciation (e.g., convert “OpenAI” to katakana) before synthesis.
• 🤝 Grok & Gemini Compatibility: Removes OpenAI-specific params from the OpenAI-style endpoint, so Grok, Gemini, and other API-compatible models work out of the box.

You can learn how to setup ChatdollKit by watching this video that runs the demo scene(including chat with ChatGPT):https://www.youtube.com/watch?v=rRtm18QSJtc

To run the demo for version 0.8, please follow the steps below after importing the dependencies:

• Open sceneDemo/Demo08.
• SelectAIAvatarVRM object in scene.
• Set OpenAI API key to following components on inspector:
  • ChatGPTService
  • OpenSpeechSynthesizer
  • OpenAISpeechListener
• Run on Unity Editor.
• Say "こんにちは" or word longer than 3 characters.

• 📦 Setup New Project
  • Import dependencies
  • Resource preparation
  • AIAvatarVRM prefab
  • ModelController
  • Animator
  • AIAvatar
  • LLM Service
  • Speech Service
  • Microphone Controller
  • Run
• 🎓 LLM Service
  • Basic Settings
  • Facial Expressions
  • Animations
  • Pause in Speech
  • User Defined Tag
  • Multi Modal
  • Chain of Thought Prompting
  • Long-Term Memory
• 🗣️ Speech Synthesizer (Text-to-Speech)
  • Voice Prefetch Mode
  • Make custom SpeechSynthesizer
  • Performance and Quality Tuning
  • Preprocessing
• 🎧 Speech Listener (Speech-to-Text)
  • Settings on AIAvatar Inspector
  • Downsampling
  • Using AzureStreamSpeechListener
  • Using Silero VAD
• ⏰ Wake Word Detection
  • Wake Words
  • Cancel Words
  • Interrupt Words
  • Ignore Words
  • Wake Length
• ⚡️ AI Agent (Tool Call)
• 🎙️ Devices
  • Microphone
  • Camera
• 🥰 3D Model Control
  • Idle Animations
  • Control by Script
• 🎚️ UI Components
• 🎮 Control from External Programs
  • ChatdollKit Remote Client
• 🌐 Run on WebGL
• 🔄 Migration from 0.7.x
• ❤️ Thanks

The steps for setting up with a VRM model are as follows. For instructions on using models for VRChat, refer toREADME v0.7.7.

⚠️CAUTION: Do not use the SRP (Scriptable Render Pipeline) project template in Unity. UniVRM, which ChatdollKit depends on, does not support SRP.

Download the latest version ofChatdollKit.unitypackage and import it into your Unity project after import dependencies;

• Burst from Unity Package Manager (Window > Package Manager)
• UniTask(Tested on Ver.2.5.4)
• uLipSync(Tested on v3.1.0)
• UniVRM(v0.127.2)
• ChatdollKit VRM Extension
• JSON.NET: If your project doesn't have JSON.NET, add it from Package Manager > [+] > Add package from git URL... > com.unity.nuget.newtonsoft-json
• Azure Speech SDK: (Option) Required forAzureStreamSpeechListener: real-time speech recognition using a stream.

Add 3D model to the scene and adjust as you like. Also install required resources for the 3D model like shaders etc.

And, import animation clips. In this README, I useAnime Girls Idle Animations Free that is also used in demo. I believe it is worth for you to purchase the pro edition👍

Add theChatdollKit/Prefabs/AIAvatarVRM prefab to the scene. And, create EventSystem to use UI components.

SelectSetup ModelController in the context menu of ModelController.

SelectSetup Animator in the context menu of ModelController and select the folder that contains animation clips or their parent folder. In this case put animation clips in01_Idles and03_Others ontoBase Layer for override blending,02_Layers ontoAdditive Layer for additive blending.

Next, see theBase Layer of newly created AnimatorController in the folder you selected. Confirm the value for transition to the state you want to set it for idle animation.

Lastly, set the value toIdle Animation Value on the inspector of ModelController.

On the inspector ofAIAvatar, setWake Word to start conversation (e.g. hello / こんにちは🇯🇵),Cancel Word to stop comversation (e.g. stop / おしまい🇯🇵),Error Voice andError Face that will be shown when error occured (e.g. Something wrong / 調子が悪いみたい🇯🇵).

Prefix / Suffix Allowance is the allowable length for additional characters before or after the wake word. For example, if the wake word is "Hello" and the allowance is 4 characters, the phrase "Ah, Hello!" will still be detected as the wake word.

Attach the component corresponding to the LLM service fromChatdollKit/Scripts/LLM and set the required fields like API keys and system prompts. In this example, we use ChatGPT, but the framework also supports Claude, Gemini, and Dify.

Attach theSpeechListener component fromChatdollKit/Scripts/SpeechListener for speech recognition and theSpeechSynthesizer component fromChatdollKit/Scripts/SpeechSynthesizer for speech synthesis. Configure the necessary fields like API keys and language codes. EnablingPrintResult in the SpeechListener settings will output recognized speech to the log, useful for debugging.

AddChatdollKit/Prefabs/Runtime/MicrophoneController to your scene. This provides a UI to adjust the minimum volume for speech recognition. If the environment is noisy, you can slide it to the left to filter out background noise.

Press Play button of Unity editor. You can see the model starts with idling animation and blinking.

• Adjust the microphone volume slider if necessary.
• Say the word you set toWake Word on inspector. (e.g. hello / こんにちは🇯🇵)
• Your model will reply "Hi there!" or something.

Enjoy👍

We support ChatGPT, Claude, Gemini, and Dify as text generation AI services. Experimental support for Command R is also available, but it is unstable. To use LLM services, attach the LLMService component you want to use fromChatdollKit/Scripts/LLM to the AIAvatar object and check theIsEnabled box. If other LLMServices are already attached, make sure to uncheck theIsEnabled box for those you don't plan to use.

You can configure parameters like API keys and system prompts directly on the attached LLMService in the inspector. For more details of these parameters, please refer to the API references for the LLM services.

You can autonomously control facial expressions according to the conversation content.

To control expressions, include tags like[face:ExpressionName] in the AI responses, which can be set through system prompts. Here's an example of a system prompt:

You have four expressions: 'Joy', 'Angry', 'Sorrow', 'Fun' and 'Surprised'.If you want to express a particular emotion, please insert it at the beginning of the sentence like [face:Joy].Example[face:Joy]Hey, you can see the ocean! [face:Fun]Let's go swimming.

The expression names must be understandable by the AI. Make sure they match exactly, including case sensitivity, with the expressions defined in the VRM model.

You can also control gestures (referred to as animations) autonomously based on the conversation content.

To control animations, include tags like[anim:AnimationName] in the AI responses, and set the instructions in the system prompt. Here's an example:

You can express your emotions through the following animations:- angry_hands_on_waist- brave_hand_on_chest- calm_hands_on_back- concern_right_hand_front- energetic_right_fist_up- energetic_right_hand_piece- pitiable_right_hand_on_back_head- surprise_hands_open_front- walking- waving_arm- look_away- nodding_once- swinging_bodyIf you want to express emotions with gestures, insert the animation into the response message like [anim:waving_arm].Example[anim:waving_arm]Hey, over here!

The animation names must be clear to the AI for it to understand the intended gesture.

To link the specified animation name to the animation defined in theAnimator Controller, register them inModelController through code as shown below:

// BasemodelController.RegisterAnimation("angry_hands_on_waist",newModel.Animation("BaseParam",0,3.0f));modelController.RegisterAnimation("brave_hand_on_chest",newModel.Animation("BaseParam",1,3.0f));modelController.RegisterAnimation("calm_hands_on_back",newModel.Animation("BaseParam",2,3.0f));modelController.RegisterAnimation("concern_right_hand_front",newModel.Animation("BaseParam",3,3.0f));modelController.RegisterAnimation("energetic_right_fist_up",newModel.Animation("BaseParam",4,3.0f));modelController.RegisterAnimation("energetic_right_hand_piece",newModel.Animation("BaseParam",5,3.0f));modelController.RegisterAnimation("pitiable_right_hand_on_back_head",newModel.Animation("BaseParam",7,3.0f));modelController.RegisterAnimation("surprise_hands_open_front",newModel.Animation("BaseParam",8,3.0f));modelController.RegisterAnimation("walking",newModel.Animation("BaseParam",9,3.0f));modelController.RegisterAnimation("waving_arm",newModel.Animation("BaseParam",10,3.0f));// AdditivemodelController.RegisterAnimation("look_away",newModel.Animation("BaseParam",6,3.0f,"AGIA_Layer_look_away_01","Additive Layer"));modelController.RegisterAnimation("nodding_once",newModel.Animation("BaseParam",6,3.0f,"AGIA_Layer_nodding_once_01","Additive Layer"));modelController.RegisterAnimation("swinging_body",newModel.Animation("BaseParam",6,3.0f,"AGIA_Layer_swinging_body_01","Additive Layer"));

If you use Animation Girl Idle Animations or its free edition, you can register animations easily:

modelController.RegisterAnimations(AGIARegistry.GetAnimations(animationCollectionKey));

You can insert pauses in the character's speech to make conversations feel more natural and human-like.

To control the length of pauses, include tags like[pause:seconds] in the AI responses, which can be set through system prompts. The specified number of seconds can be a float value, allowing precise control of the pause duration at that point in the dialogue. Here's an example of a system prompt:

You can insert pauses in the character's speech to make conversations feel more natural and human-like.Example:Hey, it's a beautiful day outside! [pause:1.5] What do you think we should do?

Besides expressions and animations, you can execute actions based on developer-defined tags. Include the instructions to insert tags in the system prompt and implementHandleExtractedTags.

Here's an example of switching room lighting on/off during the conversation:

If you want switch room light on or off, insert language tag like [light:on].Example:[light:off]OK, I will turn off the light. Good night.

dialogProcessor.LLMServiceExtensions.HandleExtractedTags=(tags,session)=>{if(tags.ContainsKey("light")){varlightCommand=tags["light"];if(lightCommand.lower()=="on"){// Turn on the lightDebug.Log($"Turn on the light");}elseif(lightCommand.lower()=="off"){// Turn off the lightDebug.Log($"Turn off the light");}else{Debug.LogWarning($"Unprocessable command:{lightCommand}");}}};

You can include images from cameras or files in requests to the LLM. Include the image binary data under the keyimageBytes in thepayloads argument ofDialogProcessor.StartDialogAsync.

Additionally, you can enable the system to autonomously capture images when required based on the user's speech. To achieve this, add the tag[vision:camera] in the AI response by configuring it in the system prompt, and implement the image capture process for when this tag is received in the LLM service.

You can use camera to get what you see.When the user wants to you to see something, insert [vision:camera] into your response message.Exampleuser: Look! I bought this today.assistant: [vision:camera]Let me see.

gameObject.GetComponent<ChatGPTService>().CaptureImage=async(source)=>{if(simpleCamera!=null){try{returnawaitsimpleCamera.CaptureImageAsync();}catch(Exceptionex){Debug.LogError($"Error at CaptureImageAsync:{ex.Message}\n{ex.StackTrace}");}}returnnull;};

Chain of Thought (CoT) prompting is a technique to enhance AI performance. For more information about CoT and examples of prompts, seehttps://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/chain-of-thought .

ChatdollKit supports Chain of Thought by excluding sentences wrapped in<thinking> ~ </thinking> tags from speech synthesis.

You can customize the tag by setting a preferred word (e.g., "reason") as theThinkTag in the inspector ofLLMContentProcessor.

ChatdollKit itself does not have a built-in mechanism for managing long-term memory. However, by implementingOnStreamingEnd, it is possible to accumulate memory. Additionally, by using a tool that retrieves stored memories, the system can recall and reflect them in conversations.

The following is an example usingChatMemory.

First, to store memories, attach theExtension/ChatMemory/ChatMemoryIntegrator component to the main GameObject and set the ChatMemory service URL and a user ID. The user ID can be any value, but if you are building a service for multiple users, make sure to assign an ID that can uniquely identify each user within your service from code-behind.

Next, add the following code to an appropriate location (such asMain) so that the request and response messages are stored in ChatMemory as history when the LLM stream finishes.

usingChatdollKit.Extension.ChatMemory;varchatMemory=gameObject.GetComponent<ChatMemoryIntegrator>();dialogProcessor.LLMServiceExtensions.OnStreamingEnd+=async(text,payloads,llmSession,token)=>{chatMemory.AddHistory(llmSession.ContextId,text,llmSession.CurrentStreamBuffer,token).Forget();};

To retrieve memories and include them in the conversation, simply add theExtension/ChatMemory/ChatMemoryTool component to the main GameObject.

NOTE: ChatMemory manages what is known as episodic memory. There is also an entity calledKnowledge, which corresponds to factual information, but it is not automatically extracted or stored. Handle it manually as needed. (By default, it is included in search targets.)

We support cloud-based speech synthesis services such as Google, Azure, OpenAI, and Watson, in addition to VOICEVOX / AivisSpeech, VOICEROID, Style-Bert-VITS2, and NijiVoice for more characterful and engaging voices. To use a speech synthesis service, attachSpeechSynthesizer fromChatdollKit/Scripts/SpeechListener to the AIAvatar object and check theIsEnabled box. If otherSpeechSynthesizer components are attached, make sure to uncheck theIsEnabled box for those not in use.

You can configure parameters like API keys and endpoints on the attachedSpeechSynthesizer in the inspector. For more details of these parameters, refer to the API references of TTS services.

TheVoice Prefetch Mode determines how speech synthesis requests are managed and processed. By default, the system operates in Parallel mode. The following modes are supported:

1. Parallel (default): In this mode, multiple speech synthesis requests are sent and processed simultaneously. This ensures the fastest response times when generating multiple speech outputs in quick succession. Use this mode when latency is critical and sufficient resources are available for parallel processing.
2. Sequential: Requests are processed one at a time in the order they are enqueued. This mode is ideal for managing limited resources or ensuring strict order of speech outputs. It avoids potential concurrency issues but may result in longer wait times for subsequent requests.
3. Disabled: No prefetching is performed in this mode. Speech synthesis occurs only when explicitly triggered, making it suitable for minimal-resource scenarios or when prefetching is unnecessary.

You can change theVoice Prefetch Mode in the inspector on the SpeechSynthesizer component. Ensure the selected mode aligns with your performance and resource management requirements.

You can easily create and use a customSpeechSynthesizer for your preferred text-to-speech service. Create a class that inherits fromChatdollKit.SpeechSynthesizer.SpeechSynthesizerBase, and implement the asynchronous methodDownloadAudioClipAsync that takes astring text andDictionary<string, object> parameters, and returns anAudioClip object playable in Unity.

UniTask<AudioClip>DownloadAudioClipAsync(stringtext,Dictionary<string,object>parameters,CancellationTokencancellationToken)

Note that WebGL does not support compressed audio playback, so make sure to handle this by adjusting your code depending on the platform.

To achieve fast response times, rather than synthesizing the entire response message into speech, we split the text into smaller parts based on punctuation and progressively synthesize and play each segment. While this greatly improves performance, excessively splitting the text can reduce the quality of the speech, especially when using AI-based speech synthesis like Style-Bert-VITS2, affecting the tone and fluency.

You can balance performance and speech quality by adjusting how the text is split for synthesis in theLLMContentProcessor component's inspector.

ImplementSpeechSynthesizer.PreprocessText method to preprocess the text to synthesize.

Interface:

Func<string,Dictionary<string,object>,CancellationToken,UniTask<string>>PreprocessText;

We support cloud-based speech recognition services such as Google, Azure, and OpenAI. To use these services, attach theSpeechListener component fromChatdollKit/Scripts/SpeechListener to the AIAvatar object. Be aware that if multiple SpeechListeners are attached, they will run in parallel, so ensure that only the one you want is active.

You can configure parameters such as API keys and endpoints on the attached SpeechListener in the inspector. For details of these parameters, please refer to the API references of the respective STT services and products.

Most of theVoice Recorder Settings are controlled by theAIAvatar component, described later, so any settings in the inspector, except for those listed below, will be ignored.

Most of the settings related to the SpeechListener are configured in the inspector of theAIAvatar component.

**NOTE: **AzureStreamSpeechListener doesn't have some properties above because that control microphone by SDK DLL internally.

TheSpeechListener class supports downsampling of raw microphone input to a lower sample rate before sending input data to the STT service. This feature helps reduce audio payload size, leading to smoother transcription over limited-bandwidth networks.

You’ll find theTarget Sample Rate (int) field exposed in the Inspector of SpeechListener component:

• Set to0 (default) to use the original sample rate (no downsampling).
• Set to a positive integer (e.g.,16000) to downsample input to that rate (in Hz).

To useAzureStreamSpeechListener, some settings differ from other SpeechListeners. This is becauseAzureStreamSpeechListener controls the microphone internally through the SDK and performs transcription incrementally.

Microphone Mute By: SelectStop Listener. If this is not set, the character will listen to its own speech, disrupting the conversation.User Message Window: UncheckIs Text Animated, and setPre Gap to0 andPost Gap to around0.2.Update(): To display the recognized text incrementally, add the following code inside the Update() method:

if(aiAvatar.Mode==AIAvatar.AvatarMode.Conversation){if(!string.IsNullOrEmpty(azureStreamSpeechListener.RecognizedTextBuffer)){aiAvatar.UserMessageWindow.Show(azureStreamSpeechListener.RecognizedTextBuffer);}}

Silero VAD is a machine learning-based voice activity detection model. By using this, you can determine human voice even in noisy environments, which significantly improves the accuracy of turn-end detection in noisy conditions compared to microphone volume-based voice activity detection.

The usage procedure is as follows:

• Importonnxruntime-unity. Follow the procedure on GitHub to edit manifest.json.
• Download theSilero VAD ONNX model and place it in the StreamingAssets folder. The filename should besilero_vad.onnx.
• Download and import ChatdollKit's SileroVADExtension.
• AttachSileroVADProcessor to the object where SpeechListener is attached.
• In theAwake method of any MonoBehaviour component, set it as the voice detection function for SpeechListener.

  varsileroVad=gameObject.GetComponent<SileroVADProcessor>();sileroVad.Initialize();varspeechListener=gameObject.GetComponent<SpeechListenerBase>();speechListener.DetectVoiceFunc=sileroVad.IsVoiced;

• Place SileroVADMicrophoneButton in the scene if necessary

When executed, Silero VAD will be used for voice activity detection.

You can detect wake words as triggers to start a conversation. You can also configure settings in the AIAvatar component’s inspector for cancel words that end a conversation, or to use the length of recognized speech as a trigger instead of specific phrases.

The conversation starts when this phrase is recognized. You can register multiple wake words. Except for the following items, settings will be ignored in versions 0.8 and later.

The conversation ends when this phrase is recognized. You can register multiple cancel words.

The character stop speaking and start listening user's request. You can register multiple interrupt words. (e.g. "Wait")

NOTE: In the AIAvatar's inspector, selectThreshold underMicrophone Mute By to allow ChatdollKit to listen your voice while the character is speaking.

You can register strings to be ignored when determining whether the recognized speech matches a wake word or cancel word. This is useful if you don’t want to consider the presence or absence of punctuation.

You can start a conversation based on the length of the recognized text, rather than specific phrases. This feature is disabled when the value is0. For example, in Idle mode, you can resume the conversation using text length instead of a wake word, and in Sleep mode, the conversation can resume with the wake word.

Using the Tool Call (Function Calling) feature provided by the LLM, you can develop AI characters that function as AI agents, rather than simply engaging in conversation.

By creating a component that implementsITool or extendsToolBase and attaching it to the AIAvatar object, it will automatically be recognized as a tool and executed when needed. To create a custom tool, defineFunctionName andFunctionDescription, and implement theGetToolSpec method, which returns the function definition, and theExecuteFunction method, which handles the function’s process. For details, refer toChatdollKit/Examples/WeatherTool.

NOTE: SeeMigration from FunctionSkill to Tool if your project has custom LLMFunctionSkills.

While ChatdollKit natively supports simple tool calls, it also provides integration with server-side AI agents to enable more agentic behaviors.

Specifically, ChatdollKit allows you to call AI agents through RESTful APIs by registering them as anLLMService. This lets you send requests and receive responses without needing to be aware of the agentic processes happening behind the scenes.
Currently,Dify andAIAvatarKit are supported. You can use them by attaching eitherDifyService orAIAvatarKitService, configuring their settings, and enabling theIsEnabled flag.

We provide a device control mechanism. Currently, microphones and cameras are supported.

TheMicrophoneManager component captures audio from the microphone and makes the audio waveform data available to other components. It is primarily intended for use with the SpeechListener, but you can also register and use recording sessions through theStartRecordingSession method in custom user-implemented components.

The following are the settings that can be configured in the inspector.

We provide theSimpleCamera prefab, which packages features such as image capture, preview display, and camera switching. Since the way cameras are handled varies by device, this is provided experimentally. For details, refer to the prefab and the scripts attached to it.

TheModelController component controls the gestures, facial expressions, and speech of 3D models.

Idle animations are looped while the model is waiting. To run the desired motion, register it in the state machine of the Animator Controller and configure the transition conditions by setting the parameter name as theIdle Animation Key and the value as theIdle Animation Value in theModelController inspector.

To register multiple motions and randomly switch between them at regular intervals, use theAddIdleAnimation method in the code as shown below. The first argument is theAnimation object to be executed,weight is the multiplier for the appearance probability, andmode is only specified if you want to display the animation in a particular model state. The constructor of theAnimation class takes the parameter name as the first argument, the value as the second, and the duration (in seconds) as the third.

modelController.AddIdleAnimation(newAnimation("BaseParam",2,5f));modelController.AddIdleAnimation(newAnimation("BaseParam",6,5f),weight:2);modelController.AddIdleAnimation(newAnimation("BaseParam",99,5f),mode:"sleep");

This section is under construction. Essentially, you create anAnimatedVoiceRequest object and callModelController.AnimatedSay. TheAIAvatar internally makes requests that combine animations, expressions, and speech, so refer to that for guidance.

We provide UI component prefabs commonly used in voice-interactive AI character applications. You can use them by simply adding them to the scene. For configuration details, refer to the demo.

• FPSManager: Displays the current frame rate. You can also set the target frame rate using this component.
• MicrophoneController: A slider to adjust the microphone's noise gate.
• RequestInput: A text box for inputting requests. It also provides buttons for retrieving images from the file system and for launching the camera.
• SimpleCamera: A component that handles image capture and preview display from the camera. You can also capture images without showing the preview.

You can send requests to the ChatdollKit application from external programs using socket communication or from JavaScript. This feature enables new use cases such as AI Vtuber streaming, remote avatar customer service, and hybrid character operations combining AI and human interaction.AttachChatdollKit/Scripts/Network/SocketServer to the AIAvatar object and set the port number (e.g., 8080) to control using socket communication, or, attachChatdollKit/Scripts/IO/JavaScriptMessageHandler to control from JavaScript.

Additionally, to handle dialog requests over the network, attach theChatdollKit/Scripts/Dialog/DialogPriorityManager to the AIAvatar object. To process requests that make the character perform gestures, facial expressions, or speech created by humans instead of AI responses, attach theChatdollKit/Scripts/Model/ModelRequestBroker to the AIAvatar object.

Below is a code example for using both of the above components.

// Configure message handler for remote control#pragma warning disableCS1998#ifUNITY_WEBGL&&!UNITY_EDITORgameObject.GetComponent<JavaScriptMessageHandler>().OnDataReceived=async(message)=>{HandleExternalMessage(message,"JavaScript");};#elsegameObject.GetComponent<SocketServer>().OnDataReceived=async(message)=>{HandleExternalMessage(message,"SocketServer");};#endif#pragma warning restoreCS1998

privatevoidHandleExternalMessage(ExternalInboundMessagemessage,stringsource){// Assign actions based on the request's Endpoint and Operationif(message.Endpoint=="dialog"){if(message.Operation=="start"){if(source=="JavaScript"){dialogPriorityManager.SetRequest(message.Text,message.Payloads,0);}else{dialogPriorityManager.SetRequest(message.Text,message.Payloads,message.Priority);}}elseif(message.Operation=="clear"){dialogPriorityManager.ClearDialogRequestQueue(message.Priority);}}elseif(message.Endpoint=="model"){modelRequestBroker.SetRequest(message.Text);}}

TheSocketServer is designed to receive arbitrary information via socket communication, so no official client program is provided. However, a Python sample code is available. Please refer to the following and adapt it to other languages or platforms as needed.

https://gist.github.com/uezo/9e56a828bb5ea0387f90cc07f82b4c15

Or, if you want to build AITuber (AI VTuber), try AITuber demo withChatdollKit AITuber Controller that is usingSocketServer internally.

Refer to the following tips for now. We are preparing demo for WebGL.

• It takes 5-10 minutes to build. (It depends on machine spec)
• Very hard to debug. Error message doesn't show the stacktrace:To use dlopen, you need to use Emscripten’s linking support, see https://github.com/kripken/emscripten/wiki/Linking
• Built-in Async/Await doesn't work (app stops atawait) because JavaScript doesn't support threading. UseUniTask instead.
• CORS required for HTTP requests.
• Microphone is not supported. UseChatdollMicrophone that is compatible with WebGL.
• Compressed audio formats like MP3 are not supported. Use WAV in SpeechSynthesizer.
• OVRLipSync is not supported. UseuLipSync anduLipSyncWebGL instead.
• If you want to show multibyte characters in message window put the font that includes multibyte characters to your project and set it to message windows.

The easiest way is deletingAssets/ChatdollKit and import ChatdollKit unitypackage again. But if you can't do so for some reasons, you can solve errors by following steps:

1. Import the latest version of ChatdollKit unitypackage. Some errors will be shown in the console.

2. Import ChatdollKit_0.7to084Migration.unitypackage.

3. Addpartial keyword toModelController,AnimatedVoiceRequest andVoice.

4. ReplaceOnSayStart withOnSayStartMigration inDialogController.

⚠️Note: This simply suppresses error outputs and does not enable continued use of legacy code. If any parts of your project still useDialogController,LLMFunctionSkill,LLMContentSkill, orChatdollKit, replace each with the updated component as follows:

• DialogController:DialogProcessor
• LLMFunctionSkill:Tool
• LLMContentSkill:LLMContentProcessor
• ChatdollKit:AIAvatar

If your component inherits fromLLMFunctionSkillBase, you can easily migrate it to inherit fromToolBase by following these steps:

1. Change the inherited class

   ReplaceLLMFunctionSkillBase withToolBase as the base class.

   // Beforepublic class MyFunctionSkill : LLMFunctionSkillBase// Afterpublic class MyFunctionSkill : ToolBase

2. Update theExecuteFunction method signature

   Modify theExecuteFunction method’s parameters and return type as follows:

   // Beforepublic UniTask<FunctionResponse> ExecuteFunction(string argumentsJsonString, Request request, State state, User user, CancellationToken token)// Afterpublic UniTask<ToolResponse> ExecuteFunction(string argumentsJsonString, CancellationToken token)

3. Update the return type ofExecuteFunction

   ChangeFunctionResponse toToolResponse.

• uLipSync (LipSync) (c)hecomi
• UniTask (async/await integration) (c)neuecc
• UniVRM (VRM) (c)VRM Consortium / (c)Masataka SUMI for MToon