Diarize MCP | API Key Diarize connector for AI agents

CALL ANY TOOL

Submit audio for diarization, retrieve speaker-attributed transcripts, and query per-speaker segments.

diarize_create_transcription_job

Create Transcription Job

Submit a new transcription and diarization job for an audio or video URL (YouTube, X, Instagram, TikTok). Returns a job ID that can be used to check status and download results.

Parameters

Name

Type

Required

Description

url

string

Required

The URL of the audio or video content to transcribe (e.g. YouTube, X, Instagram, TikTok link)

language

string

Optional

Language code for transcription (e.g. 'en', 'es', 'fr'). Defaults to auto-detection if not provided.

num_speakers

integer

Optional

Expected number of speakers in the audio. Helps improve diarization accuracy.

schema_version

string

Optional

Optional schema version to use for tool execution

tool_version

string

Optional

Optional tool version to use for execution

diarize_download_transcript

Download Transcript

diarize_get_job_status

Get Job Status

Build your Agent

Drop the toolkit in, point it at the user, and your transcription agent can use Diarize from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["diarize"], toolNames: ["diarize_transcribe", "diarize_transcript_get", "diarize_transcripts_list"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["diarize"], toolNames: ["diarize_transcribe", "diarize_transcript_get", "diarize_transcripts_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["diarize"], toolNames: ["diarize_transcribe", "diarize_transcript_get", "diarize_transcripts_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/diarize",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Diarize.

Transcribe & retrieve

Copy the prompt

Copied

Transcribe audio at [URL].

Copy the prompt

Copied

Get the transcript for [transcript_id].

Copy the prompt

Copied

List all completed transcripts.

Copy the prompt

Copied

Show transcripts created this week.

Speaker analysis

Copy the prompt

Copied

Who spoke the most in transcript [id]?

Copy the prompt

Copied

Get all segments for speaker [speaker_id].

Copy the prompt

Copied

What was the total talk time per speaker?

Copy the prompt

Copied

Find moments where [speaker] mentioned [topic].

Pipeline & cleanup

Copy the prompt

Copied

List transcripts still processing.

Copy the prompt

Copied

Delete transcript [id] and its audio.

Copy the prompt

Copied

Which transcripts failed in the last 24 hours?

Copy the prompt

Copied

Batch transcribe: [URL1], [URL2], [URL3].

SEE HOW AUTH WORKS

Users authorize Diarize once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Diarize

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Diarize

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Diarize

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Diarize

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other transcription agents and MCP connectors. Working code, live demos, fork what fits.

SALES

Sales call prep agent

Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.

Granola

Attio

View agent

SALES

Deal intelligence agent

Combine Gong, Attio, and Slack signals to surface deal risks and next-best actions. Updated after every call.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Transcripts attributed to the wrong account

A shared Diarize API key looks fine in a demo. In production, every transcription job and speaker segment is attributed to a service account. User-level quota and data isolation break. Scalekit resolves the user's key so jobs run under the right identity.

// shared API key
key = "diarize_shared_xxx"
audit → bot_service_account
quota_filter → broken

// scalekit · per-user
key = resolve(user_id)
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Diarize today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Diarize as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Diarize api key stored?

Can I limit what the agent is allowed to do in Diarize?

What happens when a user revokes Diarize access?

Are audio files stored on Diarize servers after transcription completes?

Diarize

Tools your transcription agent reaches for on Diarize, scoped per user.