Configure Your Assistant

After creating an assistant, you’ll land on the configuration page. Here’s how to set up each section. Assistant Editor Page

Model (LLM)

The model is the AI brain powering your assistant’s responses.

Setting	Description	Default
Provider	AI provider (OpenAI, Groq, Anthropic)	OpenAI
Model	Specific model (GPT-4o, Llama 3, Claude)	GPT-4o
Temperature	Creativity level (0 = precise, 1 = creative)	0.7
Max Tokens	Maximum response length	250

For voice assistants, keep Max Tokens between 150–300. Longer responses feel unnatural in conversation.

Voice (TTS)

Controls how your assistant sounds.

Setting	Description
Provider	Voice engine (ElevenLabs, Spitch, PlayHT)
Voice	Specific voice selection
Language	Voice language (auto-detected from transcriber)
Speed	Speaking rate
Stability	Voice consistency

When using African language transcribers (Spitch), the voice provider is automatically set to match.

Transcriber (STT)

Controls how your assistant hears and understands callers.

Setting	Description	Default
Provider	STT engine (Deepgram, Spitch)	Deepgram
Model	Recognition model	Nova-2
Language	Expected caller language	English

System Prompt

The system prompt defines your assistant’s personality, knowledge, and behavior. Write clear instructions about:

Who the assistant is
What it should do
How it should respond
Any constraints or rules

You are a friendly customer support agent for Acme Corp.
Help customers with order tracking, returns, and general inquiries.
Always be polite and concise. If you can't help, offer to transfer to a human agent.

First Message

What your assistant says when it picks up a call:

Setting	Description
First Message	Opening greeting text
Mode	`assistant-speaks-first` or `user-speaks-first`

Example: “Hello! Thank you for calling Acme Corp. How can I help you today?”

Tools & Files

Enhance your assistant with:

Tools — API integrations (check order status, book appointments, etc.)
Files — Knowledge documents (PDFs, docs) for context

Custom Providers

Beyond the defaults, you can configure custom voice, STT, and LLM providers.

Custom Voice (TTS)

Custom African language providers are auto-routed through the platform. Set the provider name and voice — no manual server URL needed.

Provider	Voice IDs	Languages	Notes
Spitch	`lina`, `tunde`	yo, ha, ig, en	African language TTS
Intron	Provider-defined	Nigerian languages	Enterprise TTS
Yarngpt	`default`	yo, ha, ig, pcm	Lightweight TTS

These are auto-converted to custom-voice format with the platform’s TTS worker URL when published.

Custom Transcriber (STT)

Provider	Languages	Notes
Spitch	yo, ha, ig, en	African language STT
Intron	Nigerian languages	Enterprise STT
Yarngpt-local	yo, ha, ig, pcm	Local ASR

Custom transcribers are auto-converted to custom-transcriber format with a WebSocket connection to the platform’s STT worker.

Custom LLM & BYO Credentials

To use your own API keys for standard LLM or TTS providers (OpenAI, ElevenLabs, Anthropic, etc.):

Create a credential via the Server Credentials API or Vapi dashboard
Reference the credential UUID in your assistant’s credential_ids field

{
  "credential_ids": ["vapi-cred-uuid-1111", "vapi-cred-uuid-2222"]
}

You can also pass inline credentials for one-off setups:

{
  "credentials": [
    {
      "provider": "openai",
      "api_key": "sk-..."
    }
  ]
}

Custom Webhook URL

Set a callback URL to receive call lifecycle events:

{
  "server": {
    "url": "https://myapp.com/call-events",
    "timeout": 10,
    "secret": "my-hmac-secret"
  }
}

Saving

Click Save to persist your changes. If your assistant is already published, changes sync to the voice engine automatically.

Getting Started

Assistants

WebRTC & LiveKit

Workflows

Phone Numbers

Tools

Developer

Billing

Monitoring

Configure Your Assistant

Configure Your Assistant

Model (LLM)

Voice (TTS)

Transcriber (STT)

System Prompt

First Message

Tools & Files

Custom Providers

Custom Voice (TTS)

Custom Transcriber (STT)

Custom LLM & BYO Credentials

Custom Webhook URL

Saving

​Configure Your Assistant

​Model (LLM)

​Voice (TTS)

​Transcriber (STT)

​System Prompt

​First Message

​Tools & Files

​Custom Providers

​Custom Voice (TTS)

​Custom Transcriber (STT)

​Custom LLM & BYO Credentials

​Custom Webhook URL

​Saving

Configure Your Assistant

Model (LLM)

Voice (TTS)

Transcriber (STT)

System Prompt

First Message

Tools & Files

Custom Providers

Custom Voice (TTS)

Custom Transcriber (STT)

Custom LLM & BYO Credentials

Custom Webhook URL

Saving