Voice agents
Connect ElevenLabs Agents
Conversational AI from ElevenLabs. Point it at AgentKeyRoute so every request follows your governance profile and is recorded.
Get a key with the right protection
In the console, open Connect an app (opens in a new tab) and pick this tool. AgentKeyRoute recommends a governance profile, creates the key, and shows these same steps with your key and an allowed model filled in, plus a live test.
Setup
- Install ElevenLabs Agents
Download and install it from elevenlabs.io/app/conversational-ai. Sign in and create an agent. - Point it at the gateway
1. Dashboard → Conversational AI → Agents → your agent → LLM. 2. Provider: Custom LLM 3. Server URL: https://gateway.agentkeyroute.com/v1 4. Model ID: gpt-4.1 5. Auth → Secrets → add OPENAI_API_KEY = <your API key> 6. Save and open the test console.Replace
<your API key>with your AgentKeyRoute key.gpt-4.1is an example: use a model your key may use (GET /v1/modelslists them). - Check it works
Open ElevenLabs Agents's test / preview call and speak into it. The request appears in Requests (opens in a new tab) with the policy decision, the model that answered and what was redacted.
Good to know
- It acts autonomously, so it's registered as an autonomous workload. High-risk autonomous use waits for a person on risky requests.
- It uses the OpenAI-compatible API, so the base URL ends in
/v1. - If policy doesn't allow the model you chose for some data, the gateway answers with an allowed one.
X-AIGov-Modelnames it. - Refused? See Why was a request blocked?