Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to ElevenLabs

Scalekit connector
Open markdown

The ElevenLabs connector lets your AI agent act in each user's ElevenLabs account. Each user connects their own ElevenLabs API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 119 tools.

Tools
119
What they doRead · write · destructive
63 · 40 · 1663 read40 write16 destructive
Users sign in with

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv

  2. Set your credentials

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>

  3. Create the ElevenLabs connection

    In AgentKit > Connections, create an ElevenLabs connection. The name you give it is the connection_name your code passes. See Configure connections.

  4. Authorize a user and make your first call

    quickstart.mts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    import { createInterface } from 'node:readline/promises'
    

    const scalekit = new ScalekitClient(
      process.env.SCALEKIT_ENVIRONMENT_URL,
      process.env.SCALEKIT_CLIENT_ID,
      process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    

    const connector = 'elevenlabs'
    const identifier = 'user_123'
    

    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize ElevenLabs:', link)
    const rl = createInterface({ input: process.stdin, output: process.stdout })
    await rl.question('Press Enter after authorizing...')
    rl.close()
    

    // Make your first call
    const result = await actions.executeTool({
      connector,
      identifier,
      toolName: 'elevenlabs_get_agents_settings',
      toolInput: {},
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user opens the link once and enters their ElevenLabs credentials there. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • elevenlabs_get_agentRetrieve config for an agent.Read-only

    Get Agent

    Retrieve config for an agent. Returns an object with agent_id, name, conversation_config, metadata, platform_settings, phone_numbers, whatsapp_accounts, workflow and more. Use elevenlabs_list_agents to find the id.

    Inputs

    agent_idstringrequired
    The id of an agent. This is returned on agent creation.
    branch_idstring
    The ID of the branch to use.
    include_procedure_generated_workflow_elementsboolean
    Whether to include the workflow nodes and edges generated from structured procedures. When false, the workflow contains only authored elements.
    version_idstring
    The ID of the agent version to use.
  • elevenlabs_get_agent_environment_variableGet a specific environment variable by ID.Read-only

    Get Agent Environment Variable

    Get a specific environment variable by ID. Returns an object with label, created_at_unix_secs, updated_at_unix_secs, created_by_user_id, type, id, workspace_id, values. Use elevenlabs_list_agent_environment_variables to find the id.

    Inputs

    env_var_idstringrequired
    The ID of the env var.
  • elevenlabs_get_agent_testGet an agent response test by ID.Read-only

    Get Agent Test

    Get an agent response test by ID. Returns an object with access_info, from_conversation_metadata, dynamic_variables, chat_history, conversation_initiation_source, environment, type, success_condition and more. Use elevenlabs_list_agent_tests to find the id.

    Inputs

    test_idstringrequired
    The id of a chat response test. This is returned on test creation.
  • elevenlabs_get_agent_test_invocationGet a test invocation by ID.Read-only

    Get Agent Test Invocation

    Get a test invocation by ID. Returns an object with id, agent_id, branch_id, version_id, ran_against_draft, created_at, folder_id, repeat_count and more. Use elevenlabs_list_agent_test_invocations to find the id.

    Inputs

    test_invocation_idstringrequired
    The id of a test invocation. This is returned when tests are run.
  • elevenlabs_get_agent_toolGet tool that is available in the workspace.Read-only

    Get Agent Tool

    Get tool that is available in the workspace. Returns an object with id, tool_config, access_info, usage_stats, response_mocks. Use elevenlabs_list_agent_tools to find the id.

    Inputs

    tool_idstringrequired
    ID of the requested tool.
    environmentstring
    Environment whose values are used when the MCP server URL, headers, or auth connection reference environment variables. Mirrors the environment a conversation would run in; defaults to production.
  • elevenlabs_get_agents_settingsRetrieve Convai settings for the workspace.Read-only

    Get Agents Settings

    Retrieve Convai settings for the workspace. Returns an object with conversation_initiation_client_data_webhook, webhooks, can_use_mcp_servers, rag_retention_period_days, conversation_embedding_retention_days, default_livekit_stack.

    Inputs

    This tool takes no inputs.

  • elevenlabs_get_batch_callGet detailed information about a batch call including all recipients.Read-only

    Get Batch Call

    Get detailed information about a batch call including all recipients. Returns an object with id, phone_number_id, phone_provider, whatsapp_params, name, agent_id, branch_id, environment and more.

    Inputs

    batch_idstringrequired
    The ID of the batch.
All 134 in AI