> ## Documentation Index > Fetch the complete documentation index at: https://docs.voicebot.studio/llms.txt > Use this file to discover all available pages before exploring further. # List Multi Agents > List all multi agents. ## OpenAPI ````yaml get /api/v1/multi-agent openapi: 3.1.0 info: title: Voicebot Public API description: Public API for Voicebot Assistant Management version: 1.0.0 servers: [] security: [] paths: /api/v1/multi-agent: get: tags: - multi-agent summary: List Multi Agents description: List all multi agents. operationId: list_multi_agents_api_v1_multi_agent_get responses: '200': description: Successful Response content: application/json: schema: items: $ref: '#/components/schemas/MultiAgentResponse' type: array title: Response List Multi Agents Api V1 Multi Agent Get security: - APIKeyHeader: [] components: schemas: MultiAgentResponse: properties: id: type: string title: Id name: anyOf: - type: string - type: 'null' title: Name members: items: $ref: '#/components/schemas/SquadMemberDTO-Output' type: array title: Members members_overrides: anyOf: - $ref: '#/components/schemas/CreateAssistantRequest-Output' - type: 'null' organizationId: type: string title: Organizationid createdAt: type: string title: Createdat updatedAt: type: string title: Updatedat type: object required: - id - members - organizationId - createdAt - updatedAt title: MultiAgentResponse description: Response model for a mighty agent SquadMemberDTO-Output: properties: assistantId: anyOf: - type: string - type: 'null' title: Assistantid description: >- This is the assistant that will be used for the call. To use a transient assistant, use `assistant` instead. assistant: anyOf: - $ref: '#/components/schemas/CreateAssistantRequest-Output' - type: 'null' description: >- This is the assistant that will be used for the call. To use an existing assistant, use `assistantId` instead. assistantOverrides: anyOf: - $ref: '#/components/schemas/CreateAssistantRequest-Output' - type: 'null' description: >- This can be used to override the assistant's settings and provide values for it's template variables. assistantDestinations: anyOf: - items: $ref: '#/components/schemas/TransferDestinationAssistant-Output' type: array - type: 'null' title: Assistantdestinations description: >- These are the others assistants that this assistant can transfer to. If the assistant already has transfer call tool, these destinations are just appended to existing ones. type: object title: SquadMemberDTO CreateAssistantRequest-Output: properties: name: anyOf: - type: string - type: 'null' title: Name model: anyOf: - $ref: '#/components/schemas/CreateAssistantDtoModel-Output' - type: 'null' voice: anyOf: - $ref: '#/components/schemas/CreateAssistantDtoVoice-Output' - type: 'null' firstMessageMode: anyOf: - $ref: '#/components/schemas/CreateAssistantDtoFirstMessageMode' - type: 'null' hipaaEnabled: anyOf: - type: boolean - type: 'null' title: Hipaaenabled default: false clientMessages: anyOf: - items: type: string type: array - type: 'null' title: Clientmessages serverMessages: anyOf: - items: $ref: '#/components/schemas/CreateAssistantDtoServerMessagesItem' type: array - type: 'null' title: Servermessages silenceTimeoutSeconds: anyOf: - type: number - type: 'null' title: Silencetimeoutseconds maxDurationSeconds: anyOf: - type: number - type: 'null' title: Maxdurationseconds backgroundSound: anyOf: - $ref: '#/components/schemas/CreateAssistantDtoBackgroundSound' - type: 'null' backgroundDenoisingEnabled: anyOf: - type: boolean - type: 'null' title: Backgrounddenoisingenabled modelOutputInMessagesEnabled: anyOf: - type: boolean - type: 'null' title: Modeloutputinmessagesenabled transportConfigurations: anyOf: - items: $ref: '#/components/schemas/TransportConfigurationTwilio' type: array - type: 'null' title: Transportconfigurations firstMessage: anyOf: - type: string - type: 'null' title: Firstmessage voicemailDetection: anyOf: - $ref: '#/components/schemas/VoicemailDetection' - type: 'null' voicemailMessage: anyOf: - type: string - type: 'null' title: Voicemailmessage default: '' endCallMessage: anyOf: - type: string - type: 'null' title: Endcallmessage endCallPhrases: anyOf: - items: type: string type: array - type: 'null' title: Endcallphrases metadata: anyOf: - additionalProperties: anyOf: - {} - type: 'null' type: object - type: 'null' title: Metadata serverUrl: anyOf: - type: string - type: 'null' title: Serverurl description: >- Server URL must match either workflow.amira.bot or workflow.voicebot.studio serverUrlSecret: anyOf: - type: string - type: 'null' title: Serverurlsecret analysisPlan: anyOf: - $ref: '#/components/schemas/changedAssistantAnalysisPlan-Output' - type: 'null' artifactPlan: anyOf: - $ref: '#/components/schemas/ArtifactPlan' - type: 'null' messagePlan: anyOf: - $ref: '#/components/schemas/MessagePlan' - type: 'null' startSpeakingPlan: anyOf: - $ref: '#/components/schemas/StartSpeakingPlan' - type: 'null' stopSpeakingPlan: anyOf: - $ref: '#/components/schemas/StopSpeakingPlan' - type: 'null' monitorPlan: anyOf: - $ref: '#/components/schemas/MonitorPlan' - type: 'null' transcriber: anyOf: - $ref: '#/components/schemas/CreateAssistantDtoTranscriber' - type: 'null' dialKeypadFunctionEnabled: anyOf: - type: boolean - type: 'null' title: Dialkeypadfunctionenabled endCallFunctionEnabled: anyOf: - type: boolean - type: 'null' title: Endcallfunctionenabled forwardingPhoneNumber: anyOf: - type: string - type: 'null' title: Forwardingphonenumber type: object title: CreateAssistantRequest TransferDestinationAssistant-Output: properties: message: anyOf: - type: string - $ref: '#/components/schemas/CustomMessage-Output' - type: 'null' title: Message description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. type: $ref: '#/components/schemas/Type14' transferMode: anyOf: - $ref: '#/components/schemas/TransferMode' - type: 'null' description: >- This is the mode to use for the transfer. Defaults to `rolling-history`. - `rolling-history`: This is the default mode. It keeps the entire conversation history and appends the new assistant's system message on transfer. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) Post-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) system: assistant2 system message assistant: assistant2 first message (or model generated if firstMessageMode is set to `assistant-speaks-first-with-model-generated-message`) - `swap-system-message-in-history`: This replaces the original system message with the new assistant's system message on transfer. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) Post-transfer: system: assistant2 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) assistant: assistant2 first message (or model generated if firstMessageMode is set to `assistant-speaks-first-with-model-generated-message`) - `delete-history`: This deletes the entire conversation history on transfer. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) Post-transfer: system: assistant2 system message assistant: assistant2 first message user: Yes, please assistant: how can i help? user: i need help with my account @default 'rolling-history' assistantName: type: string title: Assistantname description: This is the assistant to transfer the call to. description: anyOf: - type: string - type: 'null' title: Description description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. type: object required: - type - assistantName title: TransferDestinationAssistant CreateAssistantDtoModel-Output: properties: messages: anyOf: - items: $ref: '#/components/schemas/Messages' type: array - type: 'null' title: Messages provider: anyOf: - $ref: '#/components/schemas/StandardModel' - type: 'null' default: standard model: anyOf: - $ref: '#/components/schemas/StandardModel' - type: 'null' default: standard tools: anyOf: - items: anyOf: - $ref: '#/components/schemas/CreateDtmfToolDTO-Output' - $ref: '#/components/schemas/CreateEndCallToolDTO-Output' - $ref: '#/components/schemas/CreateFunctionToolDTO-Output' - $ref: '#/components/schemas/CreateTransferCallToolDTO-Output' type: array - type: 'null' title: Tools description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: anyOf: - items: type: string type: array - type: 'null' title: Toolids description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. temperature: anyOf: - type: number - type: 'null' title: Temperature maxTokens: anyOf: - type: integer - type: 'null' title: Maxtokens numFastTurns: anyOf: - type: number - type: 'null' title: Numfastturns knowledgeBase: anyOf: - $ref: '#/components/schemas/KnowledgeBase' - type: 'null' fallbackModels: anyOf: - items: $ref: '#/components/schemas/StandardModel' type: array - type: 'null' title: Fallbackmodels default: - standard semanticCachingEnabled: anyOf: - type: boolean - type: 'null' title: Semanticcachingenabled emotionRecognitionEnabled: anyOf: - type: boolean - type: 'null' title: Emotionrecognitionenabled type: object title: CreateAssistantDtoModel CreateAssistantDtoVoice-Output: properties: fillerInjectionEnabled: anyOf: - type: boolean - type: 'null' title: Fillerinjectionenabled model: anyOf: - $ref: '#/components/schemas/ElevenLabsModel' - type: 'null' style: type: number title: Style voiceId: anyOf: - $ref: '#/components/schemas/ElevenLabsVoiceId' - type: 'null' language: type: string title: Language provider: type: string title: Provider default: standard stability: anyOf: - type: number - type: 'null' title: Stability similarityBoost: anyOf: - type: number - type: 'null' title: Similarityboost useSpeakerBoost: anyOf: - type: boolean - type: 'null' title: Usespeakerboost default: false enableSsmlParsing: anyOf: - type: boolean - type: 'null' title: Enablessmlparsing default: false optimizeStreamingLatency: anyOf: - type: number - type: 'null' title: Optimizestreaminglatency default: 3 chunkPlan: anyOf: - $ref: '#/components/schemas/ChunkPlan-Output' - type: 'null' type: object required: - model - style - voiceId - language - chunkPlan title: CreateAssistantDtoVoice CreateAssistantDtoFirstMessageMode: type: string enum: - assistant-speaks-first - assistant-speaks-first-with-model-generated-message - assistant-waits-for-user title: CreateAssistantDtoFirstMessageMode CreateAssistantDtoServerMessagesItem: type: string enum: - end-of-call-report title: CreateAssistantDtoServerMessagesItem description: '"end-of-call-report",' CreateAssistantDtoBackgroundSound: type: string enum: - 'off' - office title: CreateAssistantDtoBackgroundSound description: '"off", "office"' TransportConfigurationTwilio: properties: provider: type: string title: Provider default: twilio timeout: anyOf: - type: number - type: 'null' title: Timeout record: anyOf: - type: boolean - type: 'null' title: Record recordingChannels: anyOf: - $ref: >- #/components/schemas/TransportConfigurationTwilioRecordingChannels - type: 'null' type: object title: TransportConfigurationTwilio VoicemailDetection: properties: enabled: anyOf: - type: boolean - type: 'null' title: Enabled provider: anyOf: - type: string - type: 'null' title: Provider machineDetectionTimeout: anyOf: - type: integer - type: 'null' title: Machinedetectiontimeout voicemailDetectionTypes: anyOf: - items: $ref: '#/components/schemas/VoicemailDetectionTypes' type: array - type: 'null' title: Voicemaildetectiontypes default: - machine_end_beep - machine_end_silence machineDetectionSilenceTimeout: anyOf: - type: integer - type: 'null' title: Machinedetectionsilencetimeout machineDetectionSpeechThreshold: anyOf: - type: integer - type: 'null' title: Machinedetectionspeechthreshold machineDetectionSpeechEndThreshold: anyOf: - type: integer - type: 'null' title: Machinedetectionspeechendthreshold type: object title: VoicemailDetection changedAssistantAnalysisPlan-Output: properties: successEvaluationRubric: anyOf: - $ref: '#/components/schemas/Rubric' - type: 'null' description: >- This is the rubric for the success evaluation request. This outputs to `call.analysis.successEvaluation`. successEvaluationRequestTimeoutSeconds: anyOf: - type: integer - type: 'null' title: Successevaluationrequesttimeoutseconds description: >- This is the timeout for the success evaluation request. This outputs to `call.analysis.successEvaluation`. successEvaluationPrompt: anyOf: - type: string - type: 'null' title: Successevaluationprompt description: >- This is the prompt for the success evaluation request. This outputs to `call.analysis.successEvaluation`. structuredDataSchema: anyOf: - $ref: '#/components/schemas/JsonSchema' - type: 'null' description: >- This is the schema for the structured data request. This outputs to `call.analysis.structuredData`. structuredDataRequestTimeoutSeconds: anyOf: - type: integer - type: 'null' title: Structureddatarequesttimeoutseconds description: >- This is the timeout for the structured data request. This outputs to `call.analysis.structuredData`. structuredDataPrompt: anyOf: - type: string - type: 'null' title: Structureddataprompt description: >- This is the prompt for the structured data request. This outputs to `call.analysis.structuredData`. summaryPrompt: anyOf: - type: string - type: 'null' title: Summaryprompt description: >- This is the prompt for the summary request. This outputs to `call.analysis.summary`. summaryRequestTimeoutSeconds: anyOf: - type: integer - type: 'null' title: Summaryrequesttimeoutseconds description: >- This is the timeout for the summary request. This outputs to `call.analysis.summary`. type: object title: changedAssistantAnalysisPlan description: This is the analysis plan for the assistant. ArtifactPlan: properties: transcriptPlan: $ref: '#/components/schemas/TranscriptPlan' recordingEnabled: anyOf: - type: boolean - type: 'null' title: Recordingenabled videoRecordingEnabled: anyOf: - type: boolean - type: 'null' title: Videorecordingenabled recordingPath: anyOf: - type: string - type: 'null' title: Recordingpath type: object required: - transcriptPlan title: ArtifactPlan MessagePlan: properties: idleMessages: anyOf: - items: type: string type: array - type: 'null' title: Idlemessages idleMessageMaxSpokenCount: anyOf: - type: number - type: 'null' title: Idlemessagemaxspokencount idleTimeoutSeconds: anyOf: - type: number - type: 'null' title: Idletimeoutseconds type: object title: MessagePlan StartSpeakingPlan: properties: waitSeconds: anyOf: - type: number - type: 'null' title: Waitseconds smartEndpointingEnabled: anyOf: - type: boolean - type: 'null' title: Smartendpointingenabled transcriptionEndpointingPlan: anyOf: - $ref: '#/components/schemas/TranscriptionEndpointingPlan' - type: 'null' type: object title: StartSpeakingPlan StopSpeakingPlan: properties: numWords: anyOf: - type: number - type: 'null' title: Numwords voiceSeconds: anyOf: - type: number - type: 'null' title: Voiceseconds backoffSeconds: anyOf: - type: number - type: 'null' title: Backoffseconds type: object title: StopSpeakingPlan MonitorPlan: properties: listenEnabled: anyOf: - type: boolean - type: 'null' title: Listenenabled controlEnabled: anyOf: - type: boolean - type: 'null' title: Controlenabled type: object title: MonitorPlan CreateAssistantDtoTranscriber: properties: provider: anyOf: - $ref: '#/components/schemas/StandardModel' - type: 'null' model: anyOf: - $ref: '#/components/schemas/StandardModel' - type: 'null' language: anyOf: - type: string - type: 'null' title: Language smartFormat: anyOf: - type: boolean - type: 'null' title: Smartformat languageDetectionEnabled: anyOf: - type: boolean - type: 'null' title: Languagedetectionenabled keywords: anyOf: - items: type: string type: array - type: 'null' title: Keywords endpointing: anyOf: - type: number - type: 'null' title: Endpointing type: object title: CreateAssistantDtoTranscriber CustomMessage-Output: properties: contents: anyOf: - items: $ref: '#/components/schemas/TextContent' type: array - type: 'null' title: Contents description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/Type13' description: This is a custom message. content: anyOf: - type: string maxLength: 1000 - type: 'null' title: Content description: >- This is the content that the assistant will say when this message is triggered. type: object required: - type title: CustomMessage Type14: type: string enum: - assistant title: Type14 TransferMode: type: string enum: - rolling-history - swap-system-message-in-history - delete-history title: TransferMode Messages: properties: content: type: string title: Content role: type: string title: Role type: object required: - content - role title: Messages StandardModel: type: string enum: - standard title: StandardModel CreateDtmfToolDTO-Output: properties: async: anyOf: - type: boolean - type: 'null' title: Async description: >- This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (`false`). examples: - false messages: anyOf: - items: anyOf: - $ref: '#/components/schemas/ToolMessageStart-Output' - $ref: '#/components/schemas/ToolMessageComplete-Output' - $ref: '#/components/schemas/ToolMessageFailed-Output' - $ref: '#/components/schemas/ToolMessageDelayed-Output' type: array - type: 'null' title: Messages description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. type: $ref: '#/components/schemas/Type7' description: The type of tool. "dtmf" for DTMF tool. function: anyOf: - $ref: '#/components/schemas/OpenAIFunction-Output' - type: 'null' description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. server: anyOf: - $ref: '#/components/schemas/Server' - type: 'null' description: >- This is the server that will be hit when this tool is requested by the model. All requests will be sent with the call object among other things. You can find more details in the Server URL documentation. This overrides the serverUrl set on the org and the phoneNumber. Order of precedence: highest tool.server.url, then assistant.serverUrl, then phoneNumber.serverUrl, then org.serverUrl. type: object required: - type title: CreateDtmfToolDTO CreateEndCallToolDTO-Output: properties: async: anyOf: - type: boolean - type: 'null' title: Async description: >- This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (`false`). examples: - false messages: anyOf: - items: anyOf: - $ref: '#/components/schemas/ToolMessageStart-Output' - $ref: '#/components/schemas/ToolMessageComplete-Output' - $ref: '#/components/schemas/ToolMessageFailed-Output' - $ref: '#/components/schemas/ToolMessageDelayed-Output' type: array - type: 'null' title: Messages description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. type: $ref: '#/components/schemas/Type8' description: The type of tool. "endCall" for End Call tool. function: anyOf: - $ref: '#/components/schemas/OpenAIFunction-Output' - type: 'null' description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. server: anyOf: - $ref: '#/components/schemas/Server' - type: 'null' description: >- This is the server that will be hit when this tool is requested by the model. All requests will be sent with the call object among other things. You can find more details in the Server URL documentation. This overrides the serverUrl set on the org and the phoneNumber. Order of precedence: highest tool.server.url, then assistant.serverUrl, then phoneNumber.serverUrl, then org.serverUrl. type: object required: - type title: CreateEndCallToolDTO CreateFunctionToolDTO-Output: properties: async: anyOf: - type: boolean - type: 'null' title: Async description: >- This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (`false`). examples: - false messages: anyOf: - items: anyOf: - $ref: '#/components/schemas/ToolMessageStart-Output' - $ref: '#/components/schemas/ToolMessageComplete-Output' - $ref: '#/components/schemas/ToolMessageFailed-Output' - $ref: '#/components/schemas/ToolMessageDelayed-Output' type: array - type: 'null' title: Messages description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. type: $ref: '#/components/schemas/Type10' description: The type of tool. "function" for Function tool. function: anyOf: - $ref: '#/components/schemas/OpenAIFunction-Output' - type: 'null' description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. server: anyOf: - $ref: '#/components/schemas/Server' - type: 'null' description: >- This is the server that will be hit when this tool is requested by the model. All requests will be sent with the call object among other things. You can find more details in the Server URL documentation. This overrides the serverUrl set on the org and the phoneNumber. Order of precedence: highest tool.server.url, then assistant.serverUrl, then phoneNumber.serverUrl, then org.serverUrl. type: object required: - type title: CreateFunctionToolDTO CreateTransferCallToolDTO-Output: properties: async: anyOf: - type: boolean - type: 'null' title: Async description: >- This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (`false`). examples: - false messages: anyOf: - items: anyOf: - $ref: '#/components/schemas/ToolMessageStart-Output' - $ref: '#/components/schemas/ToolMessageComplete-Output' - $ref: '#/components/schemas/ToolMessageFailed-Output' - $ref: '#/components/schemas/ToolMessageDelayed-Output' type: array - type: 'null' title: Messages description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. type: $ref: '#/components/schemas/Type18' destinations: anyOf: - items: anyOf: - $ref: '#/components/schemas/TransferDestinationAssistant-Output' - $ref: '#/components/schemas/TransferDestinationStep-Output' - $ref: >- #/components/schemas/app__schemas__tools__TransferDestinationNumber-Output - $ref: >- #/components/schemas/app__schemas__tools__TransferDestinationSip-Output type: array - type: 'null' title: Destinations description: >- These are the destinations that the call can be transferred to. If no destinations are provided, server.url will be used to get the transfer destination once the tool is called. function: anyOf: - $ref: '#/components/schemas/OpenAIFunction-Output' - type: 'null' description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. server: anyOf: - $ref: '#/components/schemas/Server' - type: 'null' description: >- This is the server that will be hit when this tool is requested by the model. All requests will be sent with the call object among other things. You can find more details in the Server URL documentation. This overrides the serverUrl set on the org and the phoneNumber. Order of precedence: highest tool.server.url, then assistant.serverUrl, then phoneNumber.serverUrl, then org.serverUrl. type: object required: - type title: CreateTransferCallToolDTO KnowledgeBase: properties: provider: type: string title: Provider default: canonical topK: type: number title: Topk fileIds: items: type: string type: array title: Fileids type: object required: - topK - fileIds title: KnowledgeBase ElevenLabsModel: type: string enum: - standard title: ElevenLabsModel ElevenLabsVoiceId: type: string enum: - Robert - Sascha - Kevin - Fred - Emma - Eva - Lola - Amira - Emilio - Sunita - Mohd - Jean - Mary - Tobias title: ElevenLabsVoiceId ChunkPlan-Output: properties: enabled: anyOf: - type: boolean - type: 'null' title: Enabled default: true minCharacters: anyOf: - type: number maximum: 80 minimum: 1 - type: 'null' title: Mincharacters default: 30 punctuationBoundaries: anyOf: - items: type: string type: array - type: 'null' title: Punctuationboundaries formatPlan: anyOf: - $ref: '#/components/schemas/FormatPlan-Output' - type: 'null' type: object title: ChunkPlan TransportConfigurationTwilioRecordingChannels: type: string enum: - mono - dual title: TransportConfigurationTwilioRecordingChannels VoicemailDetectionTypes: type: string enum: - machine_start - human - fax - unknown - machine_end_beep - machine_end_silence - machine_end_other title: VoicemailDetectionTypes Rubric: type: string enum: - NumericScale - DescriptiveScale - Checklist - Matrix - PercentageScale - LikertScale - AutomaticRubric - PassFail - title: Rubric JsonSchema: properties: type: $ref: '#/components/schemas/Type5' description: >- This is the type of output you'd like. `string`, `number`, `integer`, `boolean` are the primitive types and should be obvious. `array` and `object` are more interesting and quite powerful. They allow you to define nested structures. For `array`, you can define the schema of the items in the array using the `items` property. For `object`, you can define the properties of the object using the `properties` property. items: anyOf: - type: object - type: 'null' title: Items description: >- This is required if the type is "array". This is the schema of the items in the array. This is of type JsonSchema. However, Swagger doesn't support circular references. properties: anyOf: - type: object - type: 'null' title: Properties description: >- This is required if the type is "object". This specifies the properties of the object. This is a map of string to JsonSchema. However, Swagger doesn't support circular references. description: anyOf: - type: string - type: 'null' title: Description description: >- This is the description to help the model understand what it needs to output. required: anyOf: - items: type: string type: array - type: 'null' title: Required description: |- This is a list of properties that are required. This only makes sense if the type is "object". type: object required: - type title: JsonSchema TranscriptPlan: properties: enabled: anyOf: - type: boolean - type: 'null' title: Enabled userName: anyOf: - type: string - type: 'null' title: Username assistantName: anyOf: - type: string - type: 'null' title: Assistantname type: object title: TranscriptPlan TranscriptionEndpointingPlan: properties: onPunctuationSeconds: anyOf: - type: number - type: 'null' title: Onpunctuationseconds onNoPunctuationSeconds: anyOf: - type: number - type: 'null' title: Onnopunctuationseconds onNumberSeconds: anyOf: - type: number - type: 'null' title: Onnumberseconds type: object title: TranscriptionEndpointingPlan TextContent: properties: type: $ref: '#/components/schemas/Type' text: type: string title: Text language: $ref: '#/components/schemas/Language4' type: object required: - type - text - language title: TextContent Type13: type: string enum: - custom-message title: Type13 ToolMessageStart-Output: properties: contents: anyOf: - items: $ref: '#/components/schemas/TextContent' type: array - type: 'null' title: Contents description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/Type1' description: >- This message is triggered when the tool call starts. This message is never triggered for async tools. If this message is not provided, one of the default filler messages "Hold on a sec", "One moment", "Just a sec", "Give me a moment" or "This'll just take a sec" will be used. content: anyOf: - type: string maxLength: 1000 - type: 'null' title: Content description: >- This is the content that the assistant says when this message is triggered. conditions: anyOf: - items: $ref: '#/components/schemas/Condition' type: array - type: 'null' title: Conditions description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. type: object required: - type title: ToolMessageStart ToolMessageComplete-Output: properties: contents: anyOf: - items: $ref: '#/components/schemas/TextContent' type: array - type: 'null' title: Contents description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/Type2' description: >- This message is triggered when the tool call is complete. This message is triggered immediately without waiting for your server to respond for async tool calls. If this message is not provided, the model will be requested to respond. If this message is provided, only this message will be spoken and the model will not be requested to come up with a response. It's an exclusive OR. role: anyOf: - $ref: '#/components/schemas/Role' - type: 'null' description: >- This is optional and defaults to "assistant". When role=assistant, `content` is said out loud. When role=system, `content` is passed to the model in a system message. Example: system: default one assistant: user: assistant: user: assistant: user: assistant: tool called tool: your server response <--- system prompt as hint ---> model generates response which is spoken This is useful when you want to provide a hint to the model about what to say next. endCallAfterSpokenEnabled: anyOf: - type: boolean - type: 'null' title: Endcallafterspokenenabled description: >- This is an optional boolean that if true, the call will end after the message is spoken. Default is false. This is ignored if `role` is set to `system`. @default false examples: - false content: anyOf: - type: string maxLength: 1000 - type: 'null' title: Content description: >- This is the content that the assistant says when this message is triggered. conditions: anyOf: - items: $ref: '#/components/schemas/Condition' type: array - type: 'null' title: Conditions description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. type: object required: - type title: ToolMessageComplete ToolMessageFailed-Output: properties: contents: anyOf: - items: $ref: '#/components/schemas/TextContent' type: array - type: 'null' title: Contents description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/Type3' description: >- This message is triggered when the tool call fails. This message is never triggered for async tool calls. If this message is not provided, the model will be requested to respond. If this message is provided, only this message will be spoken and the model will not be requested to come up with a response. It's an exclusive OR. endCallAfterSpokenEnabled: anyOf: - type: boolean - type: 'null' title: Endcallafterspokenenabled description: >- This is an optional boolean that if true, the call will end after the message is spoken. Default is false. @default false examples: - false content: anyOf: - type: string maxLength: 1000 - type: 'null' title: Content description: >- This is the content that the assistant says when this message is triggered. conditions: anyOf: - items: $ref: '#/components/schemas/Condition' type: array - type: 'null' title: Conditions description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. type: object required: - type title: ToolMessageFailed ToolMessageDelayed-Output: properties: contents: anyOf: - items: $ref: '#/components/schemas/TextContent' type: array - type: 'null' title: Contents description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/Type4' description: >- This message is triggered when the tool call is delayed. There are the two things that can trigger this message: 1. The user talks with the assistant while your server is processing the request. Default is "Sorry, a few more seconds." 2. The server doesn't respond within `timingMilliseconds`. This message is never triggered for async tool calls. timingMilliseconds: anyOf: - type: number maximum: 120000 minimum: 100 - type: 'null' title: Timingmilliseconds description: >- The number of milliseconds to wait for the server response before saying this message. examples: - 1000 content: anyOf: - type: string maxLength: 1000 - type: 'null' title: Content description: >- This is the content that the assistant says when this message is triggered. conditions: anyOf: - items: $ref: '#/components/schemas/Condition' type: array - type: 'null' title: Conditions description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. type: object required: - type title: ToolMessageDelayed Type7: type: string enum: - dtmf title: Type7 OpenAIFunction-Output: properties: strict: anyOf: - type: boolean - type: 'null' title: Strict description: >- This is a boolean that controls whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the [OpenAI guide](https://openai.com/index/introducing-structured-outputs-in-the-api/). @default false default: false name: type: string maxLength: 64 title: Name description: >- This is the the name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. description: anyOf: - type: string maxLength: 1000 - type: 'null' title: Description description: >- This is the description of what the function does, used by the AI to choose when and how to call the function. parameters: anyOf: - $ref: '#/components/schemas/OpenAIFunctionParameters-Output' - type: 'null' description: >- These are the parameters the functions accepts, described as a JSON Schema object. See the [OpenAI guide](https://platform.openai.com/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema) for documentation about the format. Omitting parameters defines a function with an empty parameter list. type: object required: - name title: OpenAIFunction Server: properties: timeoutSeconds: anyOf: - type: number maximum: 120 minimum: 1 - type: 'null' title: Timeoutseconds description: >- This is the timeout in seconds for the request to your server. Defaults to 20 seconds. @default 20 examples: - 20 url: type: string maxLength: 2083 minLength: 1 format: uri title: Url description: >- API endpoint to send requests to. Must match specific domains and structure. secret: anyOf: - type: string - type: 'null' title: Secret description: >- This is the secret you can set that voicebot will send with every request to your server. Will be sent as a header called x-voicebot-secret. Same precedence logic as server. headers: anyOf: - type: object - type: 'null' title: Headers description: >- These are the custom headers to include in the request sent to your server. Each key-value pair represents a header name and its value. type: object required: - url title: Server Type8: type: string enum: - endCall title: Type8 Type10: type: string enum: - function title: Type10 Type18: type: string enum: - transferCall title: Type18 TransferDestinationStep-Output: properties: message: anyOf: - type: string - $ref: '#/components/schemas/CustomMessage-Output' - type: 'null' title: Message description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. type: $ref: '#/components/schemas/Type15' stepName: type: string title: Stepname description: This is the step to transfer to. description: anyOf: - type: string - type: 'null' title: Description description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. type: object required: - type - stepName title: TransferDestinationStep app__schemas__tools__TransferDestinationNumber-Output: properties: message: anyOf: - type: string - $ref: '#/components/schemas/CustomMessage-Output' - type: 'null' title: Message description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. type: $ref: '#/components/schemas/Type16' numberE164CheckEnabled: anyOf: - type: boolean - type: 'null' title: Numbere164Checkenabled description: >- This is the flag to toggle the E164 check for the `number` field. This is an advanced property which should be used if you know your use case requires it. Use cases: - `false`: To allow non-E164 numbers like `+001234567890`, `1234`, or `abc`. This is useful for dialing out to non-E164 numbers on your SIP trunks. - `true` (default): To allow only E164 numbers like `+14155551234`. This is standard for PSTN calls. If `false`, the `number` is still required to only contain alphanumeric characters (regex: `/^\+?[a-zA-Z0-9]+$/`). @default true (E164 check is enabled) default: true number: type: string maxLength: 40 minLength: 3 title: Number description: This is the phone number to transfer the call to. extension: anyOf: - type: string maxLength: 10 minLength: 1 - type: 'null' title: Extension description: >- This is the extension to dial after transferring the call to the `number`. callerId: anyOf: - type: string maxLength: 40 - type: 'null' title: Callerid description: >- This is the caller ID to use when transferring the call to the `number`. Usage: - If not provided, the caller ID will be the number the call is coming from. Example, +14151111111 calls in to and the assistant transfers out to +16470000000. +16470000000 will see +14151111111 as the caller. - To change this behavior, provide a `callerId`. - Set to '{{customer.number}}' to always use the customer's number as the caller ID. - Set to '{{phoneNumber.number}}' to always use the phone number of the assistant as the caller ID. - Set to any E164 number to always use that number as the caller ID. This needs to be a number that is owned or verified by your Transport provider like Twilio. For Twilio, you can read up more here: https://www.twilio.com/docs/voice/twiml/dial#callerid transferPlan: anyOf: - $ref: '#/components/schemas/TransferPlan-Output' - type: 'null' description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Defaults to `blind-transfer`. @default `transferPlan.mode='blind-transfer'` description: anyOf: - type: string - type: 'null' title: Description description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. type: object required: - type - number title: TransferDestinationNumber app__schemas__tools__TransferDestinationSip-Output: properties: message: anyOf: - type: string - $ref: '#/components/schemas/CustomMessage-Output' - type: 'null' title: Message description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. type: $ref: '#/components/schemas/Type17' sipUri: type: string title: Sipuri description: This is the SIP URI to transfer the call to. transferPlan: anyOf: - $ref: '#/components/schemas/TransferPlan-Output' - type: 'null' description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Defaults to `blind-transfer`. @default `transferPlan.mode='blind-transfer'` sipHeaders: anyOf: - type: object - type: 'null' title: Sipheaders description: >- These are custom headers to be added to SIP refer during transfer call. description: anyOf: - type: string - type: 'null' title: Description description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. type: object required: - type - sipUri title: TransferDestinationSip FormatPlan-Output: properties: enabled: anyOf: - type: boolean - type: 'null' title: Enabled default: true numberToDigitsCutoff: anyOf: - type: number minimum: 0 - type: 'null' title: Numbertodigitscutoff default: 2025 replacements: anyOf: - items: anyOf: - $ref: '#/components/schemas/ExactReplacement' - $ref: '#/components/schemas/RegexReplacement-Output' type: array - type: 'null' title: Replacements type: object title: FormatPlan Type5: type: string enum: - string - number - integer - boolean - array - object title: Type5 Type: type: string enum: - text title: Type Language4: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu title: Language4 Type1: type: string enum: - request-start title: Type1 Condition: properties: operator: $ref: '#/components/schemas/Operator' description: >- This is the operator you want to use to compare the parameter and value. param: type: string maxLength: 1000 title: Param description: This is the name of the parameter that you want to check. value: type: object title: Value description: This is the value you want to compare against the parameter. type: object required: - operator - param - value title: Condition Type2: type: string enum: - request-complete title: Type2 Role: type: string enum: - assistant - system title: Role Type3: type: string enum: - request-failed title: Type3 Type4: type: string enum: - request-response-delayed title: Type4 OpenAIFunctionParameters-Output: properties: type: $ref: '#/components/schemas/Type6' description: >- This must be set to 'object'. It instructs the model to return a JSON object containing the function call properties. properties: additionalProperties: $ref: '#/components/schemas/JsonSchema' type: object title: Properties description: >- This provides a description of the properties required by the function. JSON Schema can be used to specify expectations for each property. Refer to [this doc](https://ajv.js.org/json-schema.html#json-data-type) for a comprehensive guide on JSON Schema. required: anyOf: - items: type: string type: array - type: 'null' title: Required description: This specifies the properties that are required by the function. type: object required: - type - properties title: OpenAIFunctionParameters Type15: type: string enum: - step title: Type15 Type16: type: string enum: - number title: Type16 TransferPlan-Output: properties: mode: $ref: '#/components/schemas/Mode' description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Usage: - `blind-transfer`: The assistant forwards the call to the destination without any message or summary. - `blind-transfer-add-summary-to-sip-header`: The assistant forwards the call to the destination and adds a SIP header X-Transfer-Summary to the call to include the summary. - `warm-transfer-say-message`: The assistant dials the destination, delivers the `message` to the destination party, connects the customer, and leaves the call. - `warm-transfer-say-summary`: The assistant dials the destination, provides a summary of the call to the destination party, connects the customer, and leaves the call. - `warm-transfer-wait-for-operator-to-speak-first-and-then-say-message`: The assistant dials the destination, waits for the operator to speak, delivers the `message` to the destination party, and then connects the customer. - `warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary`: The assistant dials the destination, waits for the operator to speak, provides a summary of the call to the destination party, and then connects the customer. @default 'blind-transfer' message: anyOf: - type: string - $ref: '#/components/schemas/CustomMessage-Output' - type: 'null' title: Message description: >- This is the message the assistant will deliver to the destination party before connecting the customer. Usage: - Used only when `mode` is `warm-transfer-say-message` or `warm-transfer-wait-for-operator-to-speak-first-and-then-say-message`. summaryPlan: anyOf: - $ref: '#/components/schemas/SummaryPlan' - type: 'null' description: >- This is the plan for generating a summary of the call to present to the destination party. Usage: - Used only when `mode` is `warm-transfer-say-summary` or `warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary`. type: object required: - mode title: TransferPlan Type17: type: string enum: - sip title: Type17 ExactReplacement: properties: type: type: string title: Type default: exact key: type: string title: Key value: type: string maxLength: 1000 title: Value type: object required: - key - value title: ExactReplacement RegexReplacement-Output: properties: type: type: string title: Type default: regex regex: type: string title: Regex value: type: string maxLength: 1000 title: Value options: anyOf: - items: $ref: '#/components/schemas/RegexOption' type: array - type: 'null' title: Options type: object required: - regex - value title: RegexReplacement Operator: type: string enum: - eq - neq - gt - gte - lt - lte title: Operator Type6: type: string enum: - object title: Type6 Mode: type: string enum: - blind-transfer - blind-transfer-add-summary-to-sip-header - warm-transfer-say-message - warm-transfer-say-summary - warm-transfer-wait-for-operator-to-speak-first-and-then-say-message - warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary title: Mode SummaryPlan: properties: messages: anyOf: - items: type: object type: array - type: 'null' title: Messages description: >- These are the messages used to generate the summary. @default: ``` [ { "role": "system", "content": "You are an expert note-taker. You will be given a transcript of a call. Summarize the call in 2-3 sentences. DO NOT return anything except the summary." }, { "role": "user", "content": "Here is the transcript:\n\n{{transcript}}\n\n" } ]``` You can customize by providing any messages you want. Here are the template variables available: - {{transcript}}: The transcript of the call from `call.artifact.transcript`- {{systemPrompt}}: The system prompt of the call from `assistant.model.messages[type=system].content` enabled: anyOf: - type: boolean - type: 'null' title: Enabled description: >- This determines whether a summary is generated and stored in `call.analysis.summary`. Defaults to true. Usage: - If you want to disable the summary, set this to false. @default true timeoutSeconds: anyOf: - type: number maximum: 60 minimum: 1 - type: 'null' title: Timeoutseconds description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.summary` will be empty. Usage: - To guarantee the summary is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds type: object title: SummaryPlan RegexOption: properties: type: $ref: '#/components/schemas/RegexOptionType' enabled: type: boolean title: Enabled default: false type: object required: - type title: RegexOption RegexOptionType: type: string enum: - ignore-case - whole-word - multi-line title: RegexOptionType securitySchemes: APIKeyHeader: type: apiKey in: header name: X-API-Key ````