AI Providers

Avatarium supports multiple AI providers for conversation intelligence.

Available Providers

Provider	Model	Best For
Groq (default)	LLaMA 3.1 70B	Fast responses, cost-effective
OpenAI	GPT-4o	Complex reasoning
Anthropic	Claude 3.5 Sonnet	Nuanced conversations
Google	Gemini 1.5 Pro	Multimodal capabilities

Configuration

In the SDK

<Avatar
  apiKey="..."
  avatarId="aria-001"
  aiProvider="groq"
/>

Via API

curl -X POST https://api.avatarium.ai/v1/conversations \
  -H "Authorization: Bearer av_live_xxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "avatar_id": "aria-001",
    "ai_provider": "anthropic"
  }'

Provider Details

Groq (Default)

Groq is the default provider, offering the fastest response times at the lowest cost.

Model: LLaMA 3.1 70B
Latency: ~100ms
Best for: General conversations, quick responses

<Avatar aiProvider="groq" />

OpenAI

Model: GPT-4o
Latency: ~500ms
Best for: Complex reasoning, detailed responses

<Avatar aiProvider="openai" />

Anthropic

Model: Claude 3.5 Sonnet
Latency: ~400ms
Best for: Nuanced conversations, safety-critical applications

<Avatar aiProvider="anthropic" />

Google

Model: Gemini 1.5 Pro
Latency: ~400ms
Best for: Multimodal understanding, complex queries

<Avatar aiProvider="gemini" />

Custom System Prompts

Each provider can be configured with a custom system prompt:

<Avatar
  aiProvider="anthropic"
  systemPrompt={`
    You are a customer support agent for a software company.
    Be helpful, concise, and professional.
    If you don't know the answer, offer to connect the user with a human agent.
  `}
/>

Provider Fallback

Configure automatic fallback if a provider is unavailable:

<Avatar
  aiProvider="groq"
  fallbackProvider="openai"
  onProviderChange={(from, to) => {
    console.log(`Switched from ${from} to ${to}`);
  }}
/>

Customization Voice Configuration