CONNECT APP

Build with AssemblyAI

Access powerful AI models to transcribe and understand speech via a simple API.

Artificial Intelligence (AI)

API key

Visit AssemblyAI ↗ Start building

MCP

Give your agent AssemblyAI tools

Every AssemblyAI action is exposed as an MCP tool on Pipedream's remote server. Point a client at it with your end user's ID and Connect resolves that user's AssemblyAI account for each tool call — you store no tokens.

Pipedream Connect

// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": "{project_id}",
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "assemblyai",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// e.g. run Create Captions:
const result = await mcp.callTool({
  name: "assemblyai-create-captions",
  arguments: {
    transcriptId: "Transcript",
    subtitleFormat: "Subtitle Format",
  },
})

# access_token: mint a short-lived token with the Connect SDK — see the MCP guide
headers = {
    "Authorization": f"Bearer {access_token}",
    "x-pd-project-id": "{project_id}",
    "x-pd-environment": "production",
    "x-pd-external-user-id": "{external_user_id}",  # any stable ID for this user in your system
    "x-pd-app-slug": "assemblyai",
}

async with streamablehttp_client("https://remote.mcp.pipedream.net/v3", headers=headers) as (read, write, _):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()

        # e.g. run Create Captions:
        result = await session.call_tool("assemblyai-create-captions", {
            "transcriptId": "Transcript",
            "subtitleFormat": "Subtitle Format",
        })

MCP guide →

API PROXY

Call the AssemblyAI API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the AssemblyAI API with the connected user's credentials attached. You store no tokens and write no refresh logic.

Pipedream Connect

const resp = await pd.proxy.get({
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  accountId: "apn_xxxxxxx",
  url: "https://api.assemblyai.com/v2/transcript",
})

// Any allowed AssemblyAI endpoint works here. Pipedream attaches the
// connected account's credentials to the outgoing request.

# The path segment is the target URL, URL-safe base64 encoded:
# https://api.assemblyai.com/v2/transcript

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkuYXNzZW1ibHlhaS5jb20vdjIvdHJhbnNjcmlwdA?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
  -H "Authorization: Bearer {access_token}" \
  -H "x-pd-environment: production"

API proxy guide →

SDK

Run AssemblyAI actions from your backend

Connect a user's AssemblyAI account once, then run Create Captions on their behalf from your own code — TypeScript, Python, or plain HTTP.

Pipedream Connect

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "assemblyai-create-captions",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    assemblyai: { authProvisionId: "apn_xxxxxxx" },
    transcriptId: "Transcript",
    subtitleFormat: "Subtitle Format",
  },
})

from pipedream import Pipedream

pd = Pipedream(
    client_id="{oauth_client_id}",
    client_secret="{oauth_client_secret}",
    project_id="{project_id}",
    project_environment="production",
)

result = pd.actions.run(
    id="assemblyai-create-captions",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "assemblyai": {"authProvisionId": "apn_xxxxxxx"},
        "transcriptId": "Transcript",
        "subtitleFormat": "Subtitle Format",
    },
)

curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "assemblyai-create-captions",
    "configured_props": {
      "assemblyai": { "authProvisionId": "apn_xxxxxxx" },
      "transcriptId": "Transcript",
      "subtitleFormat": "Subtitle Format"
    }
  }'