AI Vtuber Creation Tool

Dashboard

AI Status: Idle

Twitch: Disconnected

Discord: Disconnected

VTube Software: Disconnected

OBS: Disconnected

Performance: N/A

Real-time Activity

Chat Messages

Waiting for chat messages...

AI Responses / Thoughts

Waiting for AI activity...

Voice Activity: Idle

Screen Perception (Preview)

Screen preview updates periodically based on Vision Model settings.

Configuration

Personality Studio

Name:

Background Story:

Traits:

System Prompt / Core Instructions:

Model Selection & Configuration

Large Language Model (LLM)

LLM Provider/Type:

Model Name/ID: Specific model identifier for the selected provider/type.

API Endpoint / Path (if applicable):

Vision Model

Vision Provider/Type: Select the model for screen perception tasks.

Vision Model Name/ID:

Screen Capture Frequency (seconds): How often to capture the screen for analysis.

Voice Settings

Text-to-Speech (TTS)

TTS Engine:

TTS Voice ID/Name:

Speed: 1.0

Pitch: 1.0

Note: Emotion mapping from AI state to TTS prosody needs configuration (Not implemented in UI yet).

Speech-to-Text (STT)

STT Engine:

STT Model Name/Path (if applicable):

Language (if applicable): Specify language code (like 'en', 'ja') or 'auto' if supported.

Enable Voice Activity Detection (VAD): Helps detect when speech starts and stops to reduce processing.

Integration Settings

Twitch

Twitch Channel Name:

Discord

Server ID:

Channel ID (for listening/speaking):

Vtubing Software

Software:

WebSocket IP Address:

WebSocket Port: Default VTube Studio port is 8001. Warudo default is 19190.

OBS Studio

OBS WebSocket IP Address:

OBS WebSocket Port:

OBS WebSocket Password:

Alert Platforms (Webhooks)

Streamlabs Webhook URL (Optional): Allows AI to react to follows, subs, etc. Requires setup in Streamlabs.

API Keys & Authentication

Enter API keys required by selected models or integrations. These should be stored securely by the application backend.

OpenAI API Key:

Anthropic API Key:

ElevenLabs API Key:

Deepgram API Key:

Twitch Bot OAuth Token: Required for sending messages. Generate via sites like twitchapps.com/tmi/ (use with caution).

Discord Bot Token:

Memory System (Long-Term)

Memory System: Determines how the AI remembers past interactions long-term.

Vector Database Settings (if enabled)

Vector DB Type:

Vector DB Path / URL: Path for local DB or URL for remote.

Embedding Model: Model used to create embeddings for memory storage/retrieval.

Relevant Memories to Retrieve: Max number of past interactions/facts to fetch for context.

Memory Summarization Prompt (Optional): Helps condense information and manage database size.

Action & Tool Configuration

Enable and configure actions the AI can perform beyond speaking.

Available Actions:

Control OBS Scenes (Requires OBS Integration)

Play Sound Effects

Web Search

Fetch Weather

More actions will appear here as they are developed or added via plugins.

Advanced Settings

Optimization Preference: Influences internal trade-offs between speed, resource usage, and response quality/complexity.

Application Log Level: Controls the verbosity of logs shown in the 'Application Logs' section.

Show AI Thought Process: Display intermediate steps like retrieved memory or action plans in the AI Response view (if supported by the pipeline).

GPU Layers (for local models like Llama.cpp): -1 for auto/max, 0 for CPU only. Requires GPU support.

Application Logs

Application logs will appear here...