Create Assistant
Create a new AI voice assistant. The assistant is automatically synced to the voice engine on creation.Endpoint
Request Body
Assistant name (max 255 characters)
Assistant description
LLM configuration
provider— AI provider (openai, groq, anthropic)model— Model name (gpt-4o, llama-3, etc.)temperature— Creativity (0-1)max_tokens— Max response lengthsystem_prompt— System instructions
Voice (TTS) configuration
provider— Voice provider (11labs, spitch, playht)voice_id— Specific voice IDlanguage— Voice language
Transcriber (STT) configuration
provider— STT provider (deepgram, spitch)model— Recognition modellanguage— Expected language
Opening greeting when the assistant picks up
assistant-speaks-first or user-speaks-firstMaximum call duration in seconds
Vapi credential UUIDs to use for provider authentication (e.g., your own OpenAI or ElevenLabs API key). Create credentials via the Server Credentials API.
Server webhook configuration
url— Callback URL for call eventstimeout— Request timeout in secondssecret— HMAC signing secret for payload verification
Example Request
Standard Provider (OpenAI LLM + ElevenLabs Voice + Deepgram STT)
Custom Provider (Spitch Voice + Spitch STT + BYO Credentials)
Custom African language providers (Spitch, Intron, Yarngpt) are auto-routed through the platform — just set the provider name. Usecredential_ids to pass your own API keys for standard providers like OpenAI or ElevenLabs.

