Update Assistant Settings with Vapi API on New Scheduled Tasks from AWS API

Pipedream makes it easy to connect APIs for Vapi, AWS and 2,500+ other apps remarkably fast.

Trigger workflow on

New Scheduled Tasks from the AWS API

Next, do this

Update Assistant Settings with the Vapi API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a AWS trigger and Vapi action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Scheduled Tasks trigger
1. Connect your AWS account
2. Select a AWS Region
3. Optional- Configure Secret
Configure the Update Assistant Settings action
1. Connect your Vapi account
2. Select a Assistant ID
3. Optional- Configure Transcriber
4. Optional- Configure Model
5. Optional- Configure Voice
6. Optional- Configure First Message
7. Optional- Select a First Message Mode
8. Optional- Configure HIPAA Enabled
9. Optional- Select one or more Client Messages
10. Optional- Select one or more Server Messages
11. Optional- Configure Silence Timeout Seconds
12. Optional- Configure Max Duration Seconds
13. Optional- Select a Background Sound
14. Optional- Configure Background Denoising Enabled
15. Optional- Configure Model Output in Messages Enabled
16. Optional- Configure Transport Configurations
17. Optional- Configure Credentials
18. Optional- Configure Name
19. Optional- Configure Voicemail Detection
20. Optional- Configure Voicemail Message
21. Optional- Configure End Call Message
22. Optional- Configure End Call Phrases
23. Optional- Configure Metadata
24. Optional- Configure Analysis Plan
25. Optional- Configure Artifact Plan
26. Optional- Configure Message Plan
27. Optional- Configure Start Speaking Plan
28. Optional- Configure Stop Speaking Plan
29. Optional- Configure Monitor Plan
30. Optional- Configure Credential IDs
31. Optional- Configure Server
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

New Scheduled Tasks on AWS

Description:Creates a Step Function State Machine to publish a message to an SNS topic at a specific timestamp. The SNS topic delivers the message to this Pipedream source, and the source emits it as a new event.

Version:0.4.2

Key:aws-new-scheduled-tasks

View on GitHub

AWS Overview#

The AWS API unlocks endless possibilities for automation with Pipedream. With this powerful combo, you can manage your AWS services and resources, automate deployment workflows, process data, and react to events across your AWS infrastructure. Pipedream offers a serverless platform for creating workflows triggered by various events that can execute AWS SDK functions, making it an efficient tool to integrate, automate, and orchestrate tasks across AWS services and other apps.

Trigger Code#

import base from "../common/scheduled.mjs";
import { toSingleLineString } from "../../common/utils.mjs";

export default {
  ...base,
  key: "aws-new-scheduled-tasks",
  name: "New Scheduled Tasks",
  description: toSingleLineString(`
    Creates a Step Function State Machine to publish a message
    to an SNS topic at a specific timestamp. The SNS topic delivers
    the message to this Pipedream source, and the source emits it as a new event.
  `),
  version: "0.4.2",
  type: "source",
  dedupe: "unique", // Dedupe on SNS message ID
  methods: {
    ...base.methods,
    getStateMachineDefinition() {
      const { PD_COMPONENT: componentId } = process.env;
      const topicArn = this.getTopicArn();
      return {
        Comment: `Task Scheduler for Pipedream component ${componentId}`,
        StartAt: "Wait",
        States: {
          Wait: {
            Comment: "Wait until specified timestamp",
            Type: "Wait",
            TimestampPath: "$.timestamp",
            Next: "SendMessageToSNS",
          },
          SendMessageToSNS: {
            Type: "Task",
            Resource: "arn:aws:states:::sns:publish",
            Parameters: {
              "TopicArn": topicArn,
              "Message.$": "$",
            },
            End: true,
          },
        },
      };
    },
    getStateMachinePermissions() {
      const topicArn = this.getTopicArn();
      const document = {
        Version: "2012-10-17",
        Statement: [
          {
            Effect: "Allow",
            Action: [
              "sns:Publish",
            ],
            Resource: [
              topicArn,
            ],
          },
        ],
      };
      const name = "publish-messages-to-pipedream-sns-topic";
      return {
        document,
        name,
      };
    },
  },
};

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
AWS	`aws`	`app`	This component uses the AWS app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
N/A	`http`	`$.interface.http`	This component uses `$.interface.http` to generate a unique URL when the component is first instantiated. Each request to the URL will trigger the `run()` method of the component.
AWS Region	`region`	`string`	Select a value from the drop down menu.
Secret	`secret`	`string`	Optional but recommended: if you enter a secret here, you must pass this value in the `secret` parameter of each HTTP POST request

Trigger Authentication#

AWS uses API keys for authentication. When you connect your AWS account, Pipedream securely stores the keys so you can easily authenticate to AWS APIs in both code and no-code steps.

Follow the AWS Instructions for creating an IAM user with an associated access and secret key.

As a best practice, attach the minimum set of IAM permissions necessary to perform the specific task in Pipedream. If your workflow only needs to perform a single API call, you should create a user and associate an IAM group / policy with permission to do only that task. You can create as many linked AWS accounts in Pipedream as you'd like.

Enter your access and secret key below.

About AWS#

Amazon Web Services (AWS) offers reliable, scalable, and inexpensive cloud computing services.

Action#

Update Assistant Settings on Vapi

Description:Updates the configuration settings for a specific assistant. [See the documentation](https://docs.vapi.ai/api-reference/assistants/update)

Version:0.0.1

Key:vapi-update-assistant-settings

View on GitHub

Vapi Overview#

The Vapi API delivers voice automation capabilities, letting you build powerful voice response systems. With Vapi, you can automate calls, send voice messages, and create dynamic interactions through speech recognition and text-to-speech. Pipedream's serverless platform allows you to integrate Vapi's API with numerous other services to automate workflows, react to events, and orchestrate complex voice-enabled processes.

Action Code#

import {
  BACKGROUND_SOUND,
  CLIENT_MESSAGE_OPTIONS,
  FIRST_MESSAGE_MODE_OPTIONS,
  SERVER_MESSAGE_OPTIONS,
} from "../../common/constants.mjs";
import {
  clearObj,
  parseObject,
} from "../../common/utils.mjs";
import vapi from "../../vapi.app.mjs";

export default {
  key: "vapi-update-assistant-settings",
  name: "Update Assistant Settings",
  description: "Updates the configuration settings for a specific assistant. [See the documentation](https://docs.vapi.ai/api-reference/assistants/update)",
  version: "0.0.1",
  type: "action",
  props: {
    vapi,
    assistantId: {
      propDefinition: [
        vapi,
        "assistantId",
      ],
    },
    transcriber: {
      type: "object",
      label: "Transcriber",
      description: "A formatted JSON object for the assistant's transcriber. **Example: { \"provider\": \"talkscriber\", \"language\": \"en\", \"model\": \"whisper\" }**. [See the documentation](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    model: {
      type: "object",
      label: "Model",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    voice: {
      type: "object",
      label: "Voice",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    firstMessage: {
      type: "string",
      label: "First Message",
      description: "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: true,
    },
    firstMessageMode: {
      type: "string",
      label: "First Message Mode",
      description: "Mode for the first message",
      optional: true,
      options: FIRST_MESSAGE_MODE_OPTIONS,
    },
    hipaaEnabled: {
      type: "boolean",
      label: "HIPAA Enabled",
      description: "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: true,
    },
    clientMessages: {
      type: "string[]",
      label: "Client Messages",
      description: "These are the messages that will be sent to your Client SDKs",
      options: CLIENT_MESSAGE_OPTIONS,
      optional: true,
    },
    serverMessages: {
      type: "string[]",
      label: "Server Messages",
      description: "These are the messages that will be sent to your Server URL",
      options: SERVER_MESSAGE_OPTIONS,
      optional: true,
    },
    silenceTimeoutSeconds: {
      type: "integer",
      label: "Silence Timeout Seconds",
      description: "How many seconds of silence to wait before ending the call.",
      optional: true,
      default: 30,
      min: 10,
      max: 3600,
    },
    maxDurationSeconds: {
      type: "integer",
      label: "Max Duration Seconds",
      description: "This is the maximum number of seconds that the call will last. When the call reaches this duration, it will be ended.",
      optional: true,
      default: 600,
      min: 10,
      max: 43200,
    },
    backgroundSound: {
      type: "string",
      label: "Background Sound",
      description: "This is the background sound in the call. Default for phone calls is 'office' and default for web calls is 'off'.",
      optional: true,
      options: BACKGROUND_SOUND,
    },
    backgroundDenoisingEnabled: {
      type: "boolean",
      label: "Background Denoising Enabled",
      description: "This enables filtering of noise and background speech while the user is talking. Default false while in beta.",
      optional: true,
    },
    modelOutputInMessagesEnabled: {
      type: "boolean",
      label: "Model Output in Messages Enabled",
      description: "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: true,
    },
    transportConfigurations: {
      type: "string[]",
      label: "Transport Configurations",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    credentials: {
      type: "string[]",
      label: "Credentials",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    name: {
      type: "string",
      label: "Name",
      description: "Name of the assistant. This is required when you want to transfer between assistants in a call.",
      optional: true,
    },
    voicemailDetection: {
      type: "object",
      label: "Voicemail Detection",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    voicemailMessage: {
      type: "string",
      label: "Voicemail Message",
      description: "This is the message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up",
      optional: true,
    },
    endCallMessage: {
      type: "string",
      label: "End Call Message",
      description: "This is the message that the assistant will say if it ends the call. If unspecified, it will hang up without saying anything",
      optional: true,
    },
    endCallPhrases: {
      type: "string[]",
      label: "End Call Phrases",
      description: "A list containing phrases that, if spoken by the assistant, will trigger the call to be hung up. Case insensitive.",
      optional: true,
    },
    metadata: {
      type: "object",
      label: "Metadata",
      description: "This is for metadata you want to store on the assistant.",
      optional: true,
    },
    analysisPlan: {
      type: "object",
      label: "Analysis Plan",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    artifactPlan: {
      type: "object",
      label: "Artifact Plan",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    messagePlan: {
      type: "object",
      label: "Message Plan",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    startSpeakingPlan: {
      type: "object",
      label: "Start Speaking Plan",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    stopSpeakingPlan: {
      type: "object",
      label: "Stop Speaking Plan",
      description: "This is the plan for when assistant should stop talking on customer interruption. **Example: {\"numWords\":0,\"voiceSeconds\":0.2,\"backoffSeconds\":1}**. [See the documentation](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    monitorPlan: {
      type: "object",
      label: "Monitor Plan",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
    credentialIds: {
      type: "string[]",
      label: "Credential IDs",
      description: "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: true,
    },
    server: {
      type: "object",
      label: "Server",
      description: "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](https://docs.vapi.ai/api-reference/assistants/update) for further details",
      optional: true,
    },
  },
  async run({ $ }) {
    const {
      vapi,
      assistantId,
      transcriber,
      model,
      voice,
      clientMessages,
      serverMessages,
      transportConfigurations,
      credentials,
      voicemailDetection,
      endCallPhrases,
      metadata,
      analysisPlan,
      artifactPlan,
      messagePlan,
      startSpeakingPlan,
      stopSpeakingPlan,
      monitorPlan,
      credentialIds,
      server,
      ...data
    } = this;

    const response = await vapi.updateAssistant({
      $,
      assistantId,
      data: clearObj({
        ...data,
        transcriber: parseObject(transcriber),
        model: parseObject(model),
        voice: parseObject(voice),
        clientMessages: parseObject(clientMessages),
        serverMessages: parseObject(serverMessages),
        transportConfigurations: parseObject(transportConfigurations),
        credentials: parseObject(credentials),
        voicemailDetection: parseObject(voicemailDetection),
        endCallPhrases: parseObject(endCallPhrases),
        metadata: parseObject(metadata),
        analysisPlan: parseObject(analysisPlan),
        artifactPlan: parseObject(artifactPlan),
        messagePlan: parseObject(messagePlan),
        startSpeakingPlan: parseObject(startSpeakingPlan),
        stopSpeakingPlan: parseObject(stopSpeakingPlan),
        monitorPlan: parseObject(monitorPlan),
        credentialIds: parseObject(credentialIds),
        server: parseObject(server),
      }),
    });
    $.export("$summary", `Updated assistant ${this.assistantId} successfully`);
    return response;
  },
};

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
Vapi	`vapi`	`app`	This component uses the Vapi app.
Assistant ID	`assistantId`	`string`	Select a value from the drop down menu.
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
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
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
First Message	`firstMessage`	`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.
First Message Mode	`firstMessageMode`	`string`	Select a value from the drop down menu:`{ "label": "Assistant Speaks First", "value": "assistant-speaks-first" }{ "label": "Assistant Waits for User", "value": "assistant-waits-for-user" }{ "label": "Assistant Speaks First with Model Generated Message", "value": "assistant-speaks-first-with-model-generated-message" }`
HIPAA Enabled	`hipaaEnabled`	`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.
Client Messages	`clientMessages`	`string[]`	Select a value from the drop down menu:`conversation-updatefunction-callfunction-call-resulthanglanguage-changedmetadatamodel-outputspeech-updatestatus-updatetranscripttool-callstool-calls-resulttransfer-updateuser-interruptedvoice-input`
Server Messages	`serverMessages`	`string[]`	Select a value from the drop down menu:`conversation-updateend-of-call-reportfunction-callhanglanguage-changedlanguage-change-detectedmodel-outputphone-call-controlspeech-updatestatus-updatetranscripttranscript[transcriptType="final"]tool-callstransfer-destination-requesttransfer-updateuser-interruptedvoice-input`
Silence Timeout Seconds	`silenceTimeoutSeconds`	`integer`	How many seconds of silence to wait before ending the call.
Max Duration Seconds	`maxDurationSeconds`	`integer`	This is the maximum number of seconds that the call will last. When the call reaches this duration, it will be ended.
Background Sound	`backgroundSound`	`string`	Select a value from the drop down menu:`{ "label": "Office", "value": "office" }{ "label": "Off", "value": "off" }`
Background Denoising Enabled	`backgroundDenoisingEnabled`	`boolean`	This enables filtering of noise and background speech while the user is talking. Default false while in beta.
Model Output in Messages Enabled	`modelOutputInMessagesEnabled`	`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.
Transport Configurations	`transportConfigurations`	`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
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
Name	`name`	`string`	Name of the assistant. This is required when you want to transfer between assistants in a call.
Voicemail Detection	`voicemailDetection`	`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
Voicemail Message	`voicemailMessage`	`string`	This is the message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up
End Call Message	`endCallMessage`	`string`	This is the message that the assistant will say if it ends the call. If unspecified, it will hang up without saying anything
End Call Phrases	`endCallPhrases`	`string[]`	A list containing phrases that, if spoken by the assistant, will trigger the call to be hung up. Case insensitive.
Metadata	`metadata`	`object`	This is for metadata you want to store on the assistant.
Analysis Plan	`analysisPlan`	`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
Artifact Plan	`artifactPlan`	`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
Message Plan	`messagePlan`	`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
Start Speaking Plan	`startSpeakingPlan`	`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
Stop Speaking Plan	`stopSpeakingPlan`	`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
Monitor Plan	`monitorPlan`	`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
Credential IDs	`credentialIds`	`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.
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

Action Authentication#

Vapi uses API keys for authentication. When you connect your Vapi account, Pipedream securely stores the keys so you can easily authenticate to Vapi APIs in both code and no-code steps.

About Vapi#

Vapi is the platform to build, test and deploy voicebots in minutes rather than months.

More Ways to Connect Vapi + AWS#

Other Popular Integrations#

Create Call with Vapi API on New DynamoDB Stream Event from AWS API

AWS + Vapi

Update Assistant Settings with Vapi API on New Scheduled Tasks from AWS API

Pipedream makes it easy to connect APIs for Vapi, AWS and 2,500+ other apps remarkably fast.

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

1-24of2,500+apps by most popular

1
-
24
of
2,500+
apps by most popular