Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to AiVOOV

Scalekit connector
Open markdown

The AiVOOV connector lets your AI agent act in each user's AiVOOV account. Each user connects their own AiVOOV API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 2 tools.

Tools
2
What they doRead · write · destructive
1 · 1 · 01 read1 write0 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 AiVOOV connection

    In AgentKit > Connections, create an AiVOOV 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 = 'aivoov'
    const identifier = 'user_123'
    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize AiVOOV:', 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: 'aivoov_voices_list',
    toolInput: {},
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user opens the link once and enters their AiVOOV 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
  • aivoov_voices_listList the text-to-speech voices available through AiVOOV (Google, Amazon, IBM and Microsoft voices), optionally for one language.Read-only

    List Voices

    List the text-to-speech voices available through AiVOOV (Google, Amazon, IBM and Microsoft voices), optionally for one language. Returns voices with voice_id, name and language. Use this to pick a voice_id for Create Audio. AiVOOV allows only 20 calls a day to this endpoint, so reuse the result.

    Inputs

    language_codestring
    Language code to filter voices by. Example: en-US.
  • aivoov_audio_createConvert one or more text segments to speech, each with its own voice and optional pitch, speaking rate and volume, joined into one audio clip.Write

    Create Audio

    Convert one or more text segments to speech, each with its own voice and optional pitch, speaking rate and volume, joined into one audio clip. Returns status, message and audio (the audio file as base64). Uses character credits from the AiVOOV account. Use List Voices first to get voice IDs.

    Inputs

    textsarrayrequired
    Text of each segment, in the same order as voice_ids. Example: ["Hello world", "How are you?"].
    voice_idsarrayrequired
    Voice ID for each text segment, in the same order as texts. Get IDs from List Voices. Example: ["a9c6e858-cbcb-4380-91e5-21cea93be41f"].
    pitch_ratesarray
    Optional pitch per segment, -50 to 50, or default. Same order as texts. Example: ["default", "10"].
    speaking_ratesarray
    Optional speaking rate per segment, 20 to 200, or default. Same order as texts. Example: ["default", "120"].
    volumesarray
    Optional volume per segment, -40 to 40, or default. Same order as texts. Example: ["default", "5"].