POST

https://api.vida.dev

/
api
/
v2
/
agent

Authorizations

token
string
queryrequired

Vida API Token

Body

application/json
type
enum<string>
required

Type for this agent

Available options:
chatAgent
title
string
required

Title for Agent

description
string
required

Some description

welcomeMessage
string

Message users see when initially visiting a agent

Array of any http links to reference for external knowledge for your agent

actions
string[]

Actions that your agent can take including instructions and settings

agentVoice
string

Agent voice model to use

agentLang
enum<string>
default: en-US

Agent language to be used for voice and transcriptions

Available options:
en-US,
es-MX,
es-ES,
es-US
agentInstructions
string

Agent instructions for user interaction. This is for chatAgents only

agentModel
string

Agent LLM model to use for its intelligence

agentS2SEngine
enum<string>

(Requires Specific Paid Plan) The Speech-to-Speech Voice engine to use for voice, AI, and transcriptions

Available options:
openai,
deepgram
agentSttEngine
enum<string>
default: deepgram

Speech to text engine for this agent

Available options:
google,
deepgram
postAnswerDtmf
string

DTMF your agent will send upon answering a call. Useful if you are forwarding calls to your agent from a platform that requires a DTMF verification before the call is connected.

waitOnAnswer
string

The amount of time in milliseconds your Agent will wait before speaking the greeting (welcomeMessage).

interruptionWordCount
integer
default: 3

how many words a caller needs to speak before it is treated as an interruption

interruptionMinimumSpeakingTime
integer
default: 3

(in seconds) How long the agent needs to be speaking before it can be interrupted

speakingTimeout
integer
default: 1200

(in milliseconds) the default amount of time between words before we consider caller speaking to be finished. Increasing this can help prevent unintentional interruptions for slow talkers.

speechProcessingDelay
integer
default: 500

(in milliseconds) the default amount of delay before processed speech is sent to the LLM for a response. Increasing this can help prevent unintentional interruptions for slow talkers. Note that this delay automatically increases and decreases depending on the number of interruptions over a period of time.

speechProcessingDelayInterruptionStep
integer
default: 500

(in milliseconds) how much speech processing delay is added per interruption.

speechProcessingDelayMaxMultiplier
integer
default: 4

the maximum number of interruptions that will influence the speech processing delay.

callerResponseTimeout
integer
default: 13

(in seconds) how much silence (nothing said by the caller) before the agent asks are you still there?.

callerResponseTimeoutHangupCounter
integer
default: 3

the maximum number of times your agent can ask are you there (callerResponseTimeout) before hanging up the call.

Response

200 - application/json
success
boolean
message
string
campaignId
string