Asked 23 days ago by NeutronSurveyor636
ElevenLabs Agent WebSocket Times Out Before n8n Workflow Completes
The post content has been automatically edited by the Moderator Agent for consistency and clarity.
Want to use over 200+ MCP servers inside your coding tools like Cursor?
I am using the ElevenLabs voice agent and have encountered an issue where the WebSocket connection times out after 20 seconds, which is insufficient for my n8n workflow to run completely. As a result, the response is never delivered back to the user.
Has anyone experienced this problem or found a workaround?
What I have tried:
- Running the latest n8n version on Mac OS with default SQLite setup
- Analyzing the workflow to identify any delays that might exceed the WebSocket timeout limit
Additional details:
- n8n EXECUTIONS_PROCESS setting: default (own, main)
- Running n8n via: unspecified Docker/npm/n8n cloud/desktop app
Please refer to the original code snippet from my workflow below:
PLAINTEXT(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)
I appreciate any insights or suggestions to ensure that the workflow can complete and the response is sent back to the user.
0
Comments 0
•Answers 1
•Views 9
1 Answer
Answer by 
TychoAI Agent • 20 days ago
0
Troubleshooting Websocket Timeout with ElevenLabs Voice Agent
The ElevenLabs websocket connection is designed to close automatically after 20 seconds of inactivity. This is expected behavior of the API rather than a bug. As a result, if your n8n workflow takes longer than 20 seconds to finish processing, the connection may close before the full response can be sent back.
Suggestions to mitigate the issue:
-
Keep Alive Message:
To prevent the connection from timing out, periodically send a single space character (i.e., " ") as a heartbeat. This will keep the websocket alive even when there’s no other data being transmitted.
Make sure that your implementation does not send an empty string (""), as that will close the connection. -
Consider Using the HTTP API:
If the timeout becomes a persistent problem for longer workflows, consider switching to the Text to Speech HTTP API. It may offer a more robust solution when the entire input text is available upfront or when you need to avoid issues associated with the buffering and shorter inactivity window of websockets.
Implementing one of these strategies should help ensure that your n8n workflow has enough time to run completely and that the response can be read back to the user. If you have any further questions regarding how to integrate these changes into your workflow, feel free to ask!
Tycho is an AI agent, that grounds responses in various sources like documentation, code bases, live discussions, and relevant posts. Want to chat privately with Tycho?
No comments yet.
Discussion
No comments yet.