Introduction - Menace Voice

Menace Voice ships official SDKs for Python and TypeScript that wrap the Menace Voice REST API and the workflow builder. Use them to create or edit agents, place outbound calls, and inspect runs from your own code.

Python — dograh-sdk on PyPI
TypeScript — @dograh/sdk on npm

Both packages are generated from the same backend OpenAPI spec, so the method surface is equivalent — only the naming convention differs (snake_case in Python, camelCase in TypeScript).

Note

The SDK package names, DograhClient class, and DOGRAH_API_KEY / DOGRAH_API_URL variables retain upstream identifiers for compatibility. Use the Menace Voice base URL explicitly; do not rename these identifiers in code.

Install#

pip install dograh-sdk

Authenticate#

Generate an API key at /api-keys (or http://localhost:3010/api-keys for self-hosted). See API Keys for details.

Both SDKs read the API key from the DOGRAH_API_KEY environment variable by default, and the base URL from DOGRAH_API_URL (defaults to http://localhost:8000). You can also pass them explicitly.

from dograh_sdk import DograhClientclient = DograhClient(    base_url="https://voice.menaceui.com",    api_key="YOUR_API_KEY",)

Note

For self-hosted deployments, swap baseUrl for your backend URL (e.g. http://localhost:8000).

Quick tour#

List the agents in your workspace:

workflows = client.list_workflows()for wf in workflows:    print(wf.id, wf.name)

Next steps#

Build an agent — assemble nodes and edges, save as a draft
Place an outbound call — trigger a call from an agent to a phone number
MCP Server — let Claude and other coding agents drive the SDK for you