Create an assistant
Authentication
Bearer authentication of the form Bearer <token>, where token is your auth token.
Request
The prompt to use for the call. This will be given to the LLM (gpt-4.1)
How the first sentence should be handled. “generated” means the LLM will generate a response based on the first_sentence instruction. “static” means the first_sentence will be spoken exactly as provided. “none” means the agent will not speak first and will wait for the user.
The voice to use for the call. You can get the list of voices using the /voices endpoint
The structured output config to use for the call. This is used to extract the data from the call (like email, name, company name, etc.).
Phone number to transfer calls to when users request to speak to a human agent in E.164 format (e.g. +1234567890).
If set, when voicemail is detected the agent will speak this message then hang up; if null, hang up immediately.
Delay in milliseconds before speaking the first sentence. Default: 400.
