---
title: "Update agent settings"
method: PUT
path: "/agents/{agentId}/settings"
tags: ["Agents"]
---

# Update agent settings

`PUT /agents/{agentId}/settings`

## Request

- Base URL: `https://api.telvana.com`
- URL: `https://api.telvana.com/agents/{agentId}/settings`
- Auth: API key in header `x-api-key`

Update agent configuration settings including call transfer, multilingual support, webhooks, and more

## Path parameters

- `agentId` string, required

## Request body

- object
  - `inboundSinglePrompt` 'null', nullable: null stops using the inbound single prompt (set in the portal), leaving inboundPrompt and inboundVoicePrompt as they are
  - `hasCallTransfer` boolean: Enable/disable call transfer
  - `hasEndCall` boolean: Enable/disable end call tool
  - `transferCallerId` 'human' | 'agent': Caller ID shown on transfer: "human" (caller number) or "agent" (business number)
  - `hasAutoInboundTransfer` boolean: Enable/disable auto inbound transfer
  - `inboundTransferNumber` string, nullable: Phone number for auto inbound transfer
  - `isMultilingual` boolean: Enable/disable multilingual support
  - `hasBargeIn` boolean: Enable/disable barge-in (interruption)
  - `hasPostConversationWebhook` boolean: Enable/disable post-conversation webhook
  - `postConversationWebhookUrl` string, nullable: URL for post-conversation webhook
  - `hasHints` boolean: Enable/disable speech recognition hints
  - `hints` string, nullable: Speech recognition hints (comma-separated)
  - `hasLanguage` boolean: Enable/disable custom language
  - `language` string, nullable: Language code (e.g., en-US)
  - `voiceId` string, nullable: Voice ID for TTS
  - `personaName` string, nullable: Spoken name of the assistant for GPT-Live voices, e.g. "Marin"
  - `businessName` string, nullable: Business name as it should be spoken; defaults to the workspace name
  - `inboundGreeting` string, nullable: Exact opening line for inbound calls on GPT-Live voices
  - `voiceScope` string, nullable: One to three sentences on what this agent helps with
  - `voiceTone` 'calm' | 'warm' | 'professional', nullable: Speaking tone preset for GPT-Live voices
  - `aiDisclosure` string, nullable: What the assistant says when asked whether it is an AI
  - `inboundVoicePrompt` string, nullable: Optional hand-written prompt for the GPT-Live voice model on inbound calls, opening line included; the full prompt still drives the backend. Empty or null clears it
  - `integrationIds` string[]: Array of integration IDs
  - `disabledToolNames` string[]: Array of disabled workspace tool names

## Response `200`

Agent settings updated successfully

- object
  - `data` object
    - `id` string, required: Unique identifier for the agent
    - `name` string, required: Agent name
    - `description` string, nullable, required: Agent description
    - `isActive` boolean, required: Whether the agent is active
    - `inboundPrompt` string, nullable, required: Prompt for inbound calls
    - `hasCallTransfer` boolean, required: Whether call transfer is enabled
    - `hasEndCall` boolean, required: Whether end call tool is enabled
    - `transferCallerId` string, required: Caller ID mode for transfers: "human" or "agent"
    - `hasAutoInboundTransfer` boolean, required: Whether auto inbound transfer is enabled
    - `inboundTransferNumber` string, nullable, required: Phone number for auto inbound transfer
    - `isMultilingual` boolean, required: Whether multilingual support is enabled
    - `hasBargeIn` boolean, required: Whether barge-in (interruption) is enabled
    - `hasPostConversationWebhook` boolean, required: Whether post-conversation webhook is enabled
    - `postConversationWebhookUrl` string, nullable, required: URL for post-conversation webhook
    - `hasHints` boolean, required: Whether speech recognition hints are enabled
    - `hints` string, nullable, required: Speech recognition hints (comma-separated)
    - `hasLanguage` boolean, required: Whether custom language is enabled
    - `language` string, nullable, required: Language code (e.g., en-US)
    - `voiceId` string, nullable, required: Voice ID for TTS
    - `personaName` string, nullable, required: Spoken assistant name (GPT-Live voice card)
    - `businessName` string, nullable, required: Spoken business name (GPT-Live voice card)
    - `inboundGreeting` string, nullable, required: Exact inbound opening line (GPT-Live voice card)
    - `voiceScope` string, nullable, required: What the agent helps with (GPT-Live voice card)
    - `voiceTone` 'calm' | 'warm' | 'professional', nullable, required: Tone preset: calm, warm or professional
    - `aiDisclosure` string, nullable, required: Answer to "are you an AI" (GPT-Live voice card)
    - `voiceCardEdited` boolean, required: True once the voice card was edited by hand; automatic derivation then leaves it
    - `inboundVoicePrompt` string, nullable, required: Hand-written GPT-Live voice prompt for inbound calls, opening line included; replaces the voice card for the voice model
    - `inboundSinglePrompt` string, nullable, required: Inbound prompt in the single-prompt template; while set, inboundPrompt and inboundVoicePrompt are rendered from it
    - `integrationIds` string[], required: Array of integration IDs
    - `disabledToolNames` string[], required: Array of disabled workspace tool names
    - `phoneNumberId` string, nullable, required: Associated phone number ID
    - `createdAt` string, date-time, required: Creation timestamp
    - `updatedAt` string, date-time, required: Last update timestamp
  - `message` string

## Other responses

- `400`: Bad request - Invalid input
- `401`: Unauthorized - Invalid API key
- `404`: Agent not found

---

[API](https://skmtc.dev/telvana/apis/telvana-api.md) · [All operations](https://skmtc.dev/telvana/apis/telvana-api/llms.txt) · [OpenAPI document](https://skmtc.dev/telvana/apis/telvana-api/revisions/a70ff9063cdf?raw)