View as Markdown
Vapi icon

Vapi ACTION

Update Assistant Settings

Updates the configuration settings for a specific assistant. See the documentation
  • Action
  • Writes data
  • Destructive
  • API key
  • SDK
  • MCP

IMPLEMENTATION

Call this tool

Connect a user's Vapi account once, then configure and run Update Assistant Settings from your backend or agent.

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "vapi-update-assistant-settings",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    vapi: { authProvisionId: "apn_xxxxxxx" },
    assistantId: "Assistant ID",
    transcriber: "Transcriber",
  },
})

console.log(result)

SCHEMA

Inputs

Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.

Update Assistant Settings inputs
Property Type Description
assistantId Assistant ID string
ID of the assistant to start a conversation with or update
Required Dynamic
transcriber Transcriber object
A formatted JSON object for the assistant's transcriber. Example: { "provider": "talkscriber", "language": "en", "model": "whisper" }. See the documentation for further details
Optional
model Model object
A formatted JSON object for the assistant's LLM. Example: {"provider": "xai", "model": "grok-beta", "emotionRecognitionEnabled": true, "knowledgeBase": {"server": {"url": "url", "timeoutSeconds": 20}}, "knowledgeBaseId": "model", "maxTokens": 1.1, "messages": [{"role": "assistant"}], "numFastTurns": 1.1, "temperature": 1.1, "toolIds": ["model"], "tools": [{"type": "transferCall", "async": false}]}. See the documentation for further details
Optional
voice Voice object
A formatted JSON object for the assistant's voice. Example: {"provider":"tavus","voiceId":"r52da2535a","callbackUrl":"voice","chunkPlan":{"enabled":true,"minCharacters":30,"punctuationBoundaries":["。",",",".","!","?",";","،",",","।","॥","|","||",",",":"],"formatPlan":{"enabled":true,"numberToDigitsCutoff":2025}},"conversationName":"voice","conversationalContext":"voice","customGreeting":"voice","fallbackPlan":{"voices":[{"provider":"tavus","voiceId":"r52da2535a"}]},"personaId":"voice","properties":{"maxCallDuration":1.1,"participantLeftTimeout":1.1,"participantAbsentTimeout":1.1,"enableRecording":true,"enableTranscription":true,"applyGreenscreen":true,"language":"language","recordingS3BucketName":"recordingS3BucketName","recordingS3BucketRegion":"recordingS3BucketRegion","awsAssumeRoleArn":"awsAssumeRoleArn"}}. See the documentation for further details
Optional
firstMessage First Message string
The first message the assistant will say or a URL to an audio file. If unspecified, assistant will wait for user to speak and use the model to respond once they speak.
Optional
firstMessageMode First Message Mode string
Mode for the first message
Optional
hipaaEnabled HIPAA Enabled boolean
When this is enabled, no logs, recordings, or transcriptions will be stored. At the end of the call, you will still receive an end-of-call-report message to store on your server.
Optional
clientMessages Client Messages string[]
These are the messages that will be sent to your Client SDKs
Optional
serverMessages Server Messages string[]
These are the messages that will be sent to your Server URL
Optional
silenceTimeoutSeconds Silence Timeout Seconds integer
How many seconds of silence to wait before ending the call.
Optional
maxDurationSeconds Max Duration Seconds integer
This is the maximum number of seconds that the call will last. When the call reaches this duration, it will be ended.
Optional
backgroundSound Background Sound string
This is the background sound in the call. Default for phone calls is 'office' and default for web calls is 'off'.
Optional
backgroundDenoisingEnabled Background Denoising Enabled boolean
This enables filtering of noise and background speech while the user is talking. Default false while in beta.
Optional
modelOutputInMessagesEnabled Model Output in Messages Enabled boolean
This determines whether the model's output is used in conversation history rather than the transcription of assistant's speech. Default false while in beta.
Optional
transportConfigurations Transport Configurations string[]
These are the configurations to be passed to the transport providers of assistant's calls, like Twilio. You can store multiple configurations for different transport providers. For a call, only the configuration matching the call transport provider is used. Example: [{"provider":"twilio","timeout":60,"record":false,"recordingChannels":"mono"}]. See the documentation for further details
Optional
credentials Credentials string[]
These are dynamic credentials that will be used for the assistant calls. By default, all the credentials are available for use in the call but you can supplement an additional credentials using this. Dynamic credentials override existing credentials. Example: [{"provider":"xai","apiKey":"credentials","name":"credentials"}]. See the documentation for further details
Optional
name Name string
Name of the assistant. This is required when you want to transfer between assistants in a call.
Optional
voicemailDetection Voicemail Detection object
These are the settings to configure or disable voicemail detection. Alternatively, voicemail detection can be configured using the model.tools=[VoicemailTool]. This uses Twilio's built-in detection while the VoicemailTool relies on the model to detect if a voicemail was reached. You can use neither of them, one of them, or both of them. By default, Twilio built-in detection is enabled while VoicemailTool is not. Example: {"provider":"twilio","voicemailDetectionTypes":["machine_end_beep","machine_end_silence"],"enabled":true,"machineDetectionTimeout":1.1,"machineDetectionSpeechThreshold":1.1,"machineDetectionSpeechEndThreshold":1.1,"machineDetectionSilenceTimeout":1.1}. See the documentation for further details
Optional
voicemailMessage Voicemail Message string
This is the message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up
Optional
endCallMessage End Call Message string
This is the message that the assistant will say if it ends the call. If unspecified, it will hang up without saying anything
Optional
endCallPhrases End Call Phrases string[]
A list containing phrases that, if spoken by the assistant, will trigger the call to be hung up. Case insensitive.
Optional
metadata Metadata object
This is for metadata you want to store on the assistant.
Optional
analysisPlan Analysis Plan object
This is the plan for analysis of assistant's calls. Stored in call.analysis. Example: {"summaryPlan":{"messages":[{"key":"value"}],"enabled":true,"timeoutSeconds":1.1},"structuredDataPlan":{"messages":[{"key":"value"}],"enabled":true,"schema":{"type":"string"},"timeoutSeconds":1.1},"successEvaluationPlan":{"rubric":"NumericScale","messages":[{"key":"value"}],"enabled":true,"timeoutSeconds":1.1}}. See the documentation for further details
Optional
artifactPlan Artifact Plan object
This is the plan for artifacts generated during assistant's calls. Stored in call.artifact. Note: recordingEnabled is currently at the root level. It will be moved to artifactPlan in the future, but will remain backwards compatible. Example: {"recordingEnabled":true,"videoRecordingEnabled":false,"transcriptPlan":{"enabled":true,"assistantName":"assistantName","userName":"userName"},"recordingPath":"recordingPath"}. See the documentation for further details
Optional
messagePlan Message Plan object
This is the plan for static predefined messages that can be spoken by the assistant during the call, like idleMessages. Note: firstMessage, voicemailMessage, and endCallMessage are currently at the root level. They will be moved to messagePlan in the future, but will remain backwards compatible. Example: {"idleMessages":["idleMessages"],"idleMessageMaxSpokenCount":1.1,"idleTimeoutSeconds":1.1}. See the documentation for further details
Optional
startSpeakingPlan Start Speaking Plan object
This is the plan for when the assistant should start talking. Example: {"waitSeconds":0.4,"smartEndpointingEnabled":false,"customEndpointingRules":[{"type":"both","assistantRegex":"customEndpointingRules","customerRegex":"customEndpointingRules","timeoutSeconds":1.1}],"transcriptionEndpointingPlan":{"onPunctuationSeconds":0.1,"onNoPunctuationSeconds":1.5,"onNumberSeconds":0.5}}. See the documentation for further details
Optional
stopSpeakingPlan Stop Speaking Plan object
This is the plan for when assistant should stop talking on customer interruption. Example: {"numWords":0,"voiceSeconds":0.2,"backoffSeconds":1}. See the documentation for further details
Optional
monitorPlan Monitor Plan object
This is the plan for real-time monitoring of the assistant's calls. Note: serverMessages, clientMessages, serverUrl and serverUrlSecret are currently at the root level but will be moved to monitorPlan in the future. Will remain backwards compatible. Example: {"listenEnabled":false,"controlEnabled":false}. See the documentation for further details
Optional
credentialIds Credential IDs string[]
These are the credentials that will be used for the assistant calls. By default, all the credentials are available for use in the call but you can provide a subset using this.
Optional
server Server object
This is where Vapi will send webhooks. You can find all webhooks available along with their shape in ServerMessage schema. Example: {"url":"url","timeoutSeconds":20,"secret":"secret","headers":{"key":"value"}}. See the documentation for further details
Optional

REFERENCE

Tool details

Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.

Registry key
vapi-update-assistant-settings
Version
0.0.5
App
Vapi
Authentication
API key
Read-only
No
Destructive
Yes
Open world
Yes