Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to Gladia

Scalekit connector
Open markdown

The Gladia connector lets your AI agent act in each user's Gladia account. Each user connects their own Gladia API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 8 tools.

Tools
8
What they doRead · write · destructive
4 · 2 · 24 read2 write2 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 Gladia connection

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

    Each user opens the link once and enters their Gladia 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
  • gladia_live_session_getGet a live transcription session with its status, parameters and final result.Read-only

    Get Live Transcription

    Get a live transcription session with its status, parameters and final result. Returns status, the session parameters and result with the transcript and any post-processing outputs. Use this after a live session ends to read what was said.

    Inputs

    job_idstringrequired
    ID of the live transcription job, returned when it was created or by the list tool. Example: 45463597-20b7-4af7-b3b3-f5fb778203ab.
  • gladia_live_sessions_listList live (real-time) transcription sessions, filtered by date or status.Read-only

    List Live Transcriptions

    List live (real-time) transcription sessions, filtered by date or status. Returns items with each session's id, status, created_at and parameters, plus pagination links. Use this to find a past live session. Use gladia_live_session_get for its transcript.

    Inputs

    after_datestring
    Only jobs after this date, ISO 8601. Combine with before_date for a range. Example: 2026-11-01T00:00:00Z.
    before_datestring
    Only jobs before this date, ISO 8601. Example: 2026-11-30T23:59:59Z.
    datestring
    Only jobs from this day, YYYY-MM-DD. Example: 2026-11-01.
    limitinteger
    Maximum jobs to return. Defaults to 20. Example: 20.
    offsetinteger
    Number of jobs to skip, for paging. Defaults to 0. Example: 0.
    statusstring
    Only jobs with this status. Example: done.one of queuedprocessingdoneerror
  • gladia_transcription_getGet a pre-recorded transcription job with its status and, when done, its full result.Read-only

    Get Transcription

    Get a pre-recorded transcription job with its status and, when done, its full result. Returns status (queued, processing, done or error), file metadata, and result with the transcript (full text and utterances) plus any summary, translation, subtitles and other add-on outputs. Use this to poll a job from gladia_transcription_create.

    Inputs

    job_idstringrequired
    ID of the pre-recorded transcription job, returned when it was created or by the list tool. Example: 45463597-20b7-4af7-b3b3-f5fb778203ab.
  • gladia_transcriptions_listList pre-recorded transcription jobs, newest first, filtered by date or status.Read-only

    List Transcriptions

    List pre-recorded transcription jobs, newest first, filtered by date or status. Returns items with each job's id, status, created_at, file metadata and request parameters, plus pagination links. Use this to find a job id. Use gladia_transcription_get for the transcript.

    Inputs

    after_datestring
    Only jobs after this date, ISO 8601. Combine with before_date for a range. Example: 2026-11-01T00:00:00Z.
    before_datestring
    Only jobs before this date, ISO 8601. Example: 2026-11-30T23:59:59Z.
    datestring
    Only jobs from this day, YYYY-MM-DD. Example: 2026-11-01.
    limitinteger
    Maximum jobs to return. Defaults to 20. Example: 20.
    offsetinteger
    Number of jobs to skip, for paging. Defaults to 0. Example: 0.
    statusstring
    Only jobs with this status. Example: done.one of queuedprocessingdoneerror
  • gladia_audio_url_uploadImport an audio or video file from a public URL into Gladia storage for later transcription.Write

    Import Audio from URL

    Import an audio or video file from a public URL into Gladia storage for later transcription. Returns audio_url (a Gladia file URL) and audio_metadata (id, filename, duration, channels). Optional: gladia_transcription_create also accepts external URLs directly. Use this to check a file's metadata or reuse it across jobs.

    Inputs

    audio_urlstringrequired
    Public URL of the audio or video file to import. Example: https://files.gladia.io/example/audio-transcription/split_infinity.wav.
  • gladia_transcription_createStart an asynchronous transcription of a pre-recorded audio or video file from a URL, with optional diarization, translation, summary, subtitles, sentiment, PII redaction and LLM prompts.Write

    Start Transcription

    Start an asynchronous transcription of a pre-recorded audio or video file from a URL, with optional diarization, translation, summary, subtitles, sentiment, PII redaction and LLM prompts. Returns the job id and a result_url. Poll gladia_transcription_get until status is done to read the transcript.

    Inputs

    audio_urlstringrequired
    URL of the file: a Gladia file URL from gladia_audio_url_upload or any public audio or video URL. Example: https://files.gladia.io/example/audio-transcription/split_infinity.wav.
    audio_to_llmboolean
    Run LLM prompts over the transcript. Example: false.
    audio_to_llm_configobject
    LLM settings when audio_to_llm is on: prompts (list of instructions) and optional model. Example: {"prompts": ["Extract the key points from the transcription"]}
    callbackboolean
    Send the result to callback_config.url when the job ends. Example: false.
    callback_configobject
    Callback settings when callback is on: url and method (POST or PUT). Example: {"url": "https://your-server.com/gladia-callback", "method": "POST"}
    custom_metadataobject
    Your own metadata stored with the job. Example: {"meeting_id": "m-123"}
    custom_spellingboolean
    Apply the spelling rules in custom_spelling_config (alpha). Example: false.
    custom_spelling_configobject
    Spelling rules: spelling_dictionary maps the wanted spelling to the variants to replace. Example: {"spelling_dictionary": {"SQL": ["Sequel"]}}
    custom_vocabularyboolean
    Use the custom vocabulary in custom_vocabulary_config (beta). Example: false.
    custom_vocabulary_configobject
    Custom vocabulary: vocabulary is a list of words or objects with value and intensity. Example: {"vocabulary": ["Scalekit", {"value": "Gladia", "intensity": 0.5}]}
    diarizationboolean
    Identify speakers. Example: true.
    diarization_configobject
    Speaker settings when diarization is on: number_of_speakers, or min_speakers and max_speakers. Example: {"min_speakers": 1, "max_speakers": 3}
    language_configobject
    Languages: languages is a list of language codes (one fixes the language, none auto-detects) and code_switching true detects language per utterance. Example: {"languages": ["en"], "code_switching": false}
    modelstring
    Transcription model. solaria-1 (default) covers 100+ languages; solaria-3 is most accurate for English, French, German, Spanish and Italian (one language only). Example: solaria-1.one of solaria-1solaria-3solaria-fusion
    named_entity_recognitionboolean
    Detect named entities (alpha). Example: false.
    pii_redactionboolean
    Redact personal data in the transcript. Example: false.
    pii_redaction_configobject
    Redaction settings: entity_types lists presets (such as GDPR or HIPAA_SAFE_HARBOR) or entity types to redact; empty redacts the default set. Example: {"entity_types": ["GDPR"]}
    punctuation_enhancedboolean
    Use enhanced punctuation (alpha). Example: false.
    sentencesboolean
    Return the transcript split into sentences. Example: true.
    sentiment_analysisboolean
    Detect sentiment and emotion per sentence. Example: false.
    subtitlesboolean
    Generate subtitles. Example: false.
    subtitles_configobject
    Subtitle settings: formats (srt, vtt) and optional duration and character limits. Example: {"formats": ["srt", "vtt"]}
    summarizationboolean
    Generate a summary. Example: true.
    summarization_configobject
    Summary settings: type is general (default), bullet_points or concise. Example: {"type": "bullet_points"}
    translationboolean
    Translate the transcript. Example: false.
    translation_configobject
    Translation settings when translation is on: target_languages (list of codes) and optional model and match_original_utterances. Example: {"target_languages": ["fr", "de"]}
  • gladia_live_session_deleteDelete a live transcription session with its recorded audio and transcript.Destructive

    Delete Live Transcription

    Delete a live transcription session with its recorded audio and transcript. Returns no content on success. Use this to remove data you no longer need.

    • Idempotent

    Inputs

    job_idstringrequired
    ID of the live transcription job, returned when it was created or by the list tool. Example: 45463597-20b7-4af7-b3b3-f5fb778203ab.
  • gladia_transcription_deleteDelete a pre-recorded transcription job with its audio file and transcript.Destructive

    Delete Transcription

    Delete a pre-recorded transcription job with its audio file and transcript. Returns no content (202 or 204) on success. Use this to remove data you no longer need.

    • Idempotent

    Inputs

    job_idstringrequired
    ID of the pre-recorded transcription job, returned when it was created or by the list tool. Example: 45463597-20b7-4af7-b3b3-f5fb778203ab.