CONNECT APP
Build with ElevenLabs
Artificial Intelligence (AI)
- API key
MCP
Give your agent ElevenLabs tools
Every ElevenLabs 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 ElevenLabs account for each tool call — you store no tokens.
// 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": "elevenlabs",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// e.g. run Add Voice:
const result = await mcp.callTool({
name: "elevenlabs-add-voice",
arguments: {
name: "Name",
files: ["File Paths or URLs"],
},
})# 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": "elevenlabs",
}
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 Add Voice:
result = await session.call_tool("elevenlabs-add-voice", {
"name": "Name",
"files": ["File Paths or URLs"],
})API PROXY
Call the ElevenLabs API directly
For an endpoint with no pre-built tool, the Connect proxy forwards your request to the ElevenLabs API with the connected user's credentials attached. You store no tokens and write no refresh logic.
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.elevenlabs.io/v1/user",
})
// Any allowed ElevenLabs 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.elevenlabs.io/v1/user
curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkuZWxldmVubGFicy5pby92MS91c2Vy?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
-H "Authorization: Bearer {access_token}" \
-H "x-pd-environment: production"SDK
Run ElevenLabs actions from your backend
Connect a user's ElevenLabs account once, then run Add Voice on their behalf from your own code — TypeScript, Python, or plain HTTP.
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: "elevenlabs-add-voice",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
elevenlabs: { authProvisionId: "apn_xxxxxxx" },
name: "Name",
files: ["File Paths or URLs"],
},
})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="elevenlabs-add-voice",
external_user_id="{external_user_id}", # any stable ID for this user in your system
configured_props={
"elevenlabs": {"authProvisionId": "apn_xxxxxxx"},
"name": "Name",
"files": ["File Paths or URLs"],
},
)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": "elevenlabs-add-voice",
"configured_props": {
"elevenlabs": { "authProvisionId": "apn_xxxxxxx" },
"name": "Name",
"files": ["File Paths or URLs"]
}
}'TOOLS
ElevenLabs actions
On-demand operations your product or agent can configure and run on behalf of a connected user.
-
Add Voice
actionAdd a voice from one or more audio files. See the documentationWritev0.0.7 -
Create Agent
actionCreate an agent in Eleventlabs. See the documentationWritev0.0.4 -
Download History Items
actionDownload one or more history items to your workflow'stmpdirectory. If one history item ID is provided, we will return a single audio file. If more than one history item IDs are provided, we will provide the history items packed into a .zip file. See the documentationRead-onlyv0.0.7 -
Get Audio From History Item
actionReturns the audio of an history item and converts it to a file. See the documentationRead-onlyv0.0.6 -
Get Models
actionGets a list of available models. See the documentationRead-onlyv0.0.5 -
Get Voices with Descriptions
actionFetches all available voices from ElevenLabs, including metadata like name, gender, accent, and category. See the documentationRead-onlyv0.0.2 -
List Agents
actionRetrieves a list of agents. See the documentationRead-onlyv0.0.2 -
List Phone Number ID Options
actionRetrieves available options for the Phone Number ID field.Read-onlyv0.0.1 -
Make Outbound Call
actionHandle an outbound call via Twilio with Elevenlabs. See the documentationWritev0.0.6 -
Text To Speech
actionRetrieve an audio file. See the documentationRead-onlyv0.0.6
EVENTS
ElevenLabs triggers
Event sources your backend can deploy for users and receive through a webhook.
MULTI-APP
Use ElevenLabs with other popular apps
Most products don't stop at one integration. Pair ElevenLabs with the other apps your users rely on, and ship use cases that span both.
- App slug
- elevenlabs
- Authentication
- API key
- Categories
- Artificial Intelligence (AI)
- Actions
- 10
- Triggers
- 1
- API proxy
- Available