Fields

provider
dropdown
default:"openai"
required
The provider of the assistant’s LLM. Options: openai, anthropic, google, deep-seek, perplexity-ai, vapi, anyscale, together-ai, inflection-ai, groq, xai, deepinfra
model
text
default:"gpt-4o-mini"
required
The model name (e.g., gpt-4o-mini, deepseek-chat, gemini-1.5-flash, claude-3-haiku-20240307) must match the provider and allowed values in Vapi’s API.
role
dropdown
default:"assistant"
required
The role of the assistant. Options: assistant, function, user, system, tool
content
text
The prompt for the assistant
name
text
The name of the assistant
silence timeout seconds
number
default:"30"
How many seconds of silence to wait before ending the call. Must be between 10 and 3600 seconds
max duration seconds
number
default:"600"
Maximum number of seconds that the call will last. Must be between 10 and 43200 seconds
recording enabled
boolean
default:"false"
Enable recording for the call
transcript enabled
boolean
default:"false"
Determines whether the transcript is stored
assistant name
text
default:"AI"
The name of the assistant in the transcript
transcript user name
text
default:"user"
The name of the user in the transcript
background denoising enabled
boolean
default:"false"
Enables filtering of noise and background speech while the user is talking
background sound
dropdown
default:"off"
Background sound in the call. Options: off, office
voicemail detection
boolean
default:"false"
Settings to configure or disable voicemail detection
voicemail message
text
Message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up
end call message
text
Message that the assistant will say if it ends the call (max 1000 characters). If unspecified, it will hang up without saying anything
end call phrases
text
List of phrases that, if spoken by the assistant, will trigger the call to be hung up. Case insensitive
first message mode
dropdown
default:"assistant-speaks-first"
Options: assistant-speaks-first, assistant-speaks-first-with-model-generated-message, assistant-waits-for-user
first message
text
First message that the assistant will say. If unspecified, assistant will wait for user to speak and use the model to respond
enable summary plan
boolean
default:"false"
Enable the plan to customize the plan for the summary
summary plan message
text
The messages used to generate the summary

Return Values

id
text
Unique identifier for the assistant
org id
text
Organization identifier
created at
date
When the assistant was created
updated at
date
When the assistant was last updated
error
boolean
Whether an error occurred
error message
text
Error message if an error occurred
error status
number
Error status code if an error occurred