Overview This workflow allows you to trigger custom logic in n8n directly from Retell's Voice Agent using Custom Functions. It captures a POST webhook from Retell every time a Voice Agent reaches a Custom Function node. You can plug in any logic—call an external API, book a meeting, update a CRM, or even return a dynamic response back to the agent. Who is it for For builders using Retell who want to extend Voice Agent functionality with real-time custom workflows or AI-generated responses. Prerequisites Have a Retell AI Account A Retell agent with a Custom Function node in its conversation flow (see template below) Set your n8n webhook URL in the Custom Function configuration (see "How to use it" below) (Optional) Familiarity with Retell's Custom Function docs Start a conversation with the agent (text or voice) Retell Agent Example To get you started, we've prepared a Retell Agent ready to be imported, that includes the call to this template. Import the agent to your Retell workspace (top-right button on your agent's page) You will need to modify the function URL in order to call your own instance.
Tags
Related workflows
See all General Automation→Tiny tiny Rss (aka tt-rss) Feed to Mastodon
Every 10 minutes look at your published news in your Tiny tiny RSS public feed and make a toot on your mastodon. You'll need: Your mastondon URL instance Your mastondon access token Your Tiny Tiny RSS public published feed URL
Register credential overwrites on startup with the n8n API
Quick Overview This workflow helps you set and maintain n8n credential overwrites by fetching credential schemas via the n8n REST API and registering overwrite values on every n8n startup using the credential overwrite endpoint. How it works Runs manually to collect your target credential type and n8n base URL for testing. Calls the n8n REST API to fetch the schema for the specified credential type so you can see which fields are available to overwrite. Triggers when n8n starts and sends a POST request to the credential overwrite endpoint to register the overwrite payload. Stores the overwrite JSON securely inside an HTTP custom auth credential and uses it as the request body to apply defaults that users cannot change in the UI. Setup Self-host n8n and set CREDENTIALS_OVERWRITE_ENDPOINT=creds-overwrite (and CREDENTIALS_OVERWRITE_PERSISTENCE=true if you run queue mode). Create an n8n API key with at least read permissions, add it as an n8n API credential, and set the correct base URL in the schema request. Enter the credential type name you want to overwrite (for example googleOAuth2Api) in the input fields used by the manual test. Create an HTTP Custom Auth credential that contains
Generate Pinterest pin copy CSV from blog RSS with OpenAI-compatible chat
Quick overview Turn your latest blog posts into Pinterest-ready pin titles, descriptions and keywords, exported as a CSV formatted for Pinterest's native bulk upload. An AI writes one conversion-focused pin per post from your RSS feed — curiosity-preserving titles under 90 characters, natural keywords, no clickbait. How it works Starts when you manually execute the workflow. Loads configuration values such as the RSS feed URL, number of posts to process, target Pinterest board name, and the AI API base URL and model. Reads the blog’s RSS feed and collects the newest N posts with their titles, links, and short snippets. Sends the post list to an OpenAI-compatible Chat Completions endpoint to generate one Pinterest pin title, description, and keyword set per post as structured JSON. Transforms the AI response into Pinterest bulk upload columns (including Title, Description, Keywords, Link, and Pinterest board) and inserts a placeholder Media URL for you to replace. Converts the rows into a CSV file and provides it for download. Setup Add an HTTP Header Auth credential for your OpenAI-compatible API (for example, Authorization: Bearer ) and select it on the AI request step. Update the