venice-ai-ultraviolet

This is an n8n community node that provides complete integration with the Venice AI API, enabling access to uncensored AI models, image generation, text-to-speech, embeddings, and more.

Features

• 🤖 Chat Completions - Access Venice's uncensored LLMs with streaming support
• 🎨 Image Generation - Create images with various models and styles
• 🖼️ Image Editing - Edit and upscale existing images
• 🎙️ Text-to-Speech - Convert text to natural-sounding speech
• 📊 Embeddings - Generate text embeddings for semantic search
• 🎭 Characters - Use pre-configured AI characters
• 🌐 Web Search - Enable web search with citations
• 🧠 Reasoning Models - Support for models with thinking capabilities

Installation

Community Node (Recommended)

1. In n8n, go to Settings > Community Nodes
2. Select Install a community node
3. Enter venice-ai-ultraviolet
4. Click Install

Manual Installation

npm install venice-ai-ultraviolet

Authentication

1. Get your API key from Venice AI
2. In n8n, add credentials:
   • Go to Credentials > New
   • Select Venice AI API
   • Enter your API key
   • Save

Supported Operations

Chat

• Complete - Create chat completions with various models
  • Streaming support
  • Function calling/tools
  • Web search integration
  • Character personalities
  • JSON response format
  • Reasoning models with thinking blocks

Image

• Generate - Text-to-image generation
• Generate Simple - OpenAI-compatible generation
• Upscale - Upscale or enhance images
• Edit - Modify images based on prompts
• List Styles - Get available style presets

Audio

• Text to Speech - Convert text to speech with multiple voices

Embedding

• Create - Generate text embeddings

Model

• List - List available models by type
• List Traits - List model traits and mappings

Character

• List - List available AI characters

Usage Examples

Chat Completion

{
  "model": "venice-uncensored",
  "messages": [
    {"role": "user", "content": "Hello, how are you?"}
  ],
  "temperature": 0.7
}

Image Generation

{
  "model": "hidream",
  "prompt": "A beautiful sunset over mountain ranges",
  "width": 1024,
  "height": 1024,
  "steps": 20
}

Text to Speech

{
  "input": "Hello, welcome to Venice AI",
  "voice": "af_sky",
  "response_format": "mp3",
  "speed": 1.0
}

Available Models

Chat Models

• venice-uncensored - Venice's flagship uncensored model
• llama-3.3-70b - Llama 3.3 70B
• qwen-2.5-vl - Vision-capable model
• deepseek-v3 - DeepSeek V3
• And many more...

Image Models

• hidream - High-quality image generation
• flux-dev - Flux development model
• venice-sd35 - Stable Diffusion 3.5
• Various specialized models

Voices (Text-to-Speech)

• Female voices: af_sky, af_nova, af_bella, etc.
• Male voices: am_echo, am_onyx, am_adam, etc.
• Multiple language support

Advanced Features

Streaming Chat Responses

Enable streaming for real-time token generation:

{
  "stream": true,
  "stream_options": {
    "include_usage": true
  }
}

Web Search Integration

Enable web search for current information:

{
  "venice_parameters": {
    "enable_web_search": "auto",
    "enable_web_citations": true
  }
}

Using Characters

Access pre-configured AI personalities:

{
  "venice_parameters": {
    "character_slug": "alan-watts"
  }
}

Function Calling

Define tools for the model to use:

{
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather information",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {"type": "string"}
          }
        }
      }
    }
  ]
}

Error Handling

The node provides detailed error messages for common issues:

• 401 - Invalid API key
• 402 - Insufficient balance
• 429 - Rate limit exceeded
• 503 - Model at capacity
• 504 - Request timeout

Rate Limits

Venice AI has different rate limits based on your plan. The node will automatically handle rate limit errors and provide appropriate feedback.

Support

• Venice AI Documentation
• GitHub Issues
• Venice AI Discord

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Changelog

0.1.0

• Initial release
• Full Venice AI API support
• Chat completions with streaming
• Image generation, editing, and upscaling
• Text-to-speech
• Embeddings
• Model and character listing