> ## Documentation Index > Fetch the complete documentation index at: https://vida.io/docs/llms.txt > Use this file to discover all available pages before exploring further. # Update Agent > Update an agent ## OpenAPI ````yaml post /api/v2/agent openapi: 3.0.0 info: version: 2.0.0 title: Vida API description: Vida API Documentation servers: - url: https://api.vida.dev description: Vida Production variables: baseUrl: default: api.vida.dev description: Production API Root security: [] paths: /api/v2/agent: post: tags: - Agents summary: Update Agent description: Update an agent requestBody: required: true content: application/json: schema: type: object required: - type - title - description properties: type: description: Type for this agent type: string enum: - chatAgent title: description: Title for Agent type: string example: Call Screener description: description: Some description type: string example: Description welcomeMessage: description: Message users see when initially visiting a agent type: string example: This brought to you by Wolf Cola links: description: >- Array of any http links to reference for external knowledge for your agent type: array items: type: string example: - https://vida.io/faq actions: description: >- Actions that your agent can take including instructions and settings type: array items: type: string example: - transfer timezone: description: >- The IANA (Internet Assigned Numbers Authority) formatted timezone your AI agent operates in. type: string example: America/Chicago, America/New_York, Europe/London, etc agentVoice: description: Agent voice model to use type: string example: en-US Female agentLang: description: Agent language to be used for voice and transcriptions type: string enum: - en-US - multi - es-MX - es-ES - es-US default: en-US agentInstructions: description: >- Agent instructions for user interaction. This is for chatAgents only type: string example: >- I want you to payout rewards for users that answer a few questions about this promotional video. agentModel: description: Agent LLM model to use for its intelligence type: string example: gpt-4o-2024-08-06 agentThinking: description: >- Optional reasoning budget for models that support thinking. Use null to disable or low for short thinking. type: string enum: - low nullable: true agentThinkingModel: description: >- Model to use for pauseAndThink function reasoning. Defaults to gpt-5.2. type: string example: gpt-5.2 postConvoForceThinking: description: >- Force post-conversation summary/reporting/spam detection to use a thinking-capable model when agentThinking is off and the selected model does not support thinking. Uses agentThinkingModel (default gpt-5.2). type: boolean example: false agentS2SEngine: description: >- (Requires Specific Paid Plan) The Speech-to-Speech Voice engine to use for voice, AI, and transcriptions type: string enum: - null - openai - gemini default: null agentSttEngine: description: Speech to text engine for this agent type: string enum: - google - deepgram - deepgramflux - openai default: deepgram agentSttSmartFormatting: description: >- Enable Deepgram smart formatting for speech-to-text (punctuation + numerals stay enabled regardless). Default true. type: boolean default: true postAnswerDtmf: description: >- 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. type: string waitOnAnswer: description: >- The amount of time in milliseconds your Agent will wait before speaking the greeting (welcomeMessage). type: integer backgroundAudio: description: >- Optional background audio to play on calls. Accepts a URL string or an object with url, loop (true or false), gain, and startAfterGreeting fields. Only HTTP(S) URLs are supported. oneOf: - type: string - type: object properties: url: type: string loop: type: boolean default: true gain: type: integer default: 0 startAfterGreeting: type: boolean default: true track: type: string enum: - bg - fx description: >- Advanced: choose track name; bg = ambient, fx = foreground. required: - url interruptionWordCount: description: >- how many words a caller needs to speak before it is treated as an interruption type: integer default: 3 interruptionMinimumSpeakingTime: description: >- (in seconds) How long the agent needs to be speaking before it can be interrupted type: integer default: 3 speakingTimeout: description: >- (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. type: integer default: 1200 speechProcessingDelay: description: >- (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. type: integer default: 500 speechProcessingDelayInterruptionStep: description: >- (in milliseconds) how much speech processing delay is added per interruption. type: integer default: 500 speechProcessingDelayMaxMultiplier: description: >- the maximum number of interruptions that will influence the speech processing delay. type: integer default: 4 callerResponseTimeout: description: >- (in seconds) how much silence (nothing said by the caller) before the agent asks _are you still there?_. type: integer default: 13 callerResponseTimeoutHangupCounter: description: >- the maximum number of times your agent can ask _are you there_ (callerResponseTimeout) before hanging up the call. type: integer default: 3 noContactInjection: description: >- Whether the contact card for the caller should be injected into the agent context type: boolean default: false noConvoHistory: description: >- Whether the call summary history for the caller should be injected into the agent context type: boolean default: false autoRecordingNotification: description: >- Whether to automatically notify callers that recording is happening: _true (string)_ means notify callers from area codes where it is legally required. _false (string)_ means never notify callers. _always (string)_ means notify every caller whether legally required or not that recording is in progress. type: string default: 'true' recordingNotificationPhrase: description: >- The phrase that will be spoken to the caller notifying them that recording is in progress: _This call is being recorded_ is the default. type: string default: This call is being recorded. preAnswerRingTime: description: >- In seconds. How many seconds should the caller experience ringing before the agent answers. Valid value range is 1-60 type: integer default: null preAnswerSkipProcessingResults: description: >- When true, pre-answer functions return their raw results directly to agent context instead of sending those results back to the LLM for another processing step. type: boolean default: false cnamAutoRejectRegex: description: >- Optional JavaScript regex string. On inbound voice calls, if the inbound SIP CNAM matches this pattern, the call is immediately rejected before answer. Reject wins if both reject and transfer match. type: string default: null cnamAutoRejectCode: description: >- Optional SIP reject code to use when cnamAutoRejectRegex matches. Defaults to 603 when omitted. type: integer default: 603 cnamAutoTransferRegex: description: >- Optional JavaScript regex string. On inbound voice calls, if the inbound SIP CNAM matches this pattern and reject did not match, the call is immediately transferred silently. type: string default: null cnamAutoTransferDestination: description: >- Destination used when cnamAutoTransferRegex matches. Accepts E.164 phone numbers or PBX/extension targets like ext:1234 or pbx:1234. type: string default: null confirmTransfers: description: Require callee to press 1 before a transfer is completed type: boolean default: false monitorTransfers: description: Continue to monitor and transcribe transferred calls. type: boolean default: false attendedTransfers: description: >- Your agent will stay on the line with the caller while transfer attempts are made. Those answering the transfer attempts will need to say Yes to accept the call. This will override the confirmTransfers option. type: boolean default: false attendedTransferBridgeTrigger: description: >- What is required to be spoken by the transferee in order for the call to be bridged. Values can be null (defaults to Yes), any, or a regex. type: string default: null transferConfirmTimeout: description: >- The length of time in seconds we will wait for confirmation after a transferred call with confirmTransfers or attendedTransfers is answered. type: integer default: 30 apps: description: Array of apps to enable for this given agent type: array default: [] items: type: object required: - appId - version - instructions properties: appId: type: string example: squareUp description: The identifier for the integrated app. version: type: string example: v1 description: The version of the app integration. instructions: type: string example: Use this app to book appointments from the user. description: Instructions for how to use the app. responses: '200': description: Successful response content: application/json: schema: type: object properties: success: type: boolean example: true message: type: string example: Agent created. campaignId: type: string example: camp931829b5857f.... security: - apiKeyAuth: [] components: securitySchemes: apiKeyAuth: type: apiKey in: query name: token description: Vida API Token ````