CONNECT APP

Build with Temi

Temi is an audio transcription service that uses computers to transcribe English audio or video into text. We also offer rich editing tools that you can use to annotate and edit your transcripts.

Language Tools

API key

Visit Temi ↗ Start building

MCP

Give your agent Temi tools

Every Temi 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 Temi 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": "temi",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// e.g. run Submit Transcription Job:
const result = await mcp.callTool({
  name: "temi-submit-transcription-job",
  arguments: {
    mediaUrl: "Media URL",
    metadata: "Metadata",
  },
})

# 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": "temi",
}

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 Submit Transcription Job:
        result = await session.call_tool("temi-submit-transcription-job", {
            "mediaUrl": "Media URL",
            "metadata": "Metadata",
        })

MCP guide →

API PROXY

Call the Temi API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Temi 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.temi.com/v1/account",
})

// Any allowed Temi 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.temi.com/v1/account

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkudGVtaS5jb20vdjEvYWNjb3VudA?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 Temi actions from your backend

Connect a user's Temi account once, then run Submit Transcription Job 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: "temi-submit-transcription-job",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    temi: { authProvisionId: "apn_xxxxxxx" },
    mediaUrl: "Media URL",
    metadata: "Metadata",
  },
})

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="temi-submit-transcription-job",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "temi": {"authProvisionId": "apn_xxxxxxx"},
        "mediaUrl": "Media URL",
        "metadata": "Metadata",
    },
)

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": "temi-submit-transcription-job",
    "configured_props": {
      "temi": { "authProvisionId": "apn_xxxxxxx" },
      "mediaUrl": "Media URL",
      "metadata": "Metadata"
    }
  }'