Feed live search data into an n8n voice agent by adding an HTTP Request node that calls the Scavio API whenever the agent needs current information to answer a caller's question. Voice agents without live data access are limited to their training cutoff and cannot answer questions about current pricing, availability, or events. This tutorial builds an n8n workflow that intercepts the agent's tool-call requests, executes a search, and returns the results as context for the voice response.
Prerequisites
- n8n instance running (self-hosted or cloud)
- A Scavio API key from scavio.dev
- An n8n voice agent workflow (Twilio, VAPI, or similar)
- Basic familiarity with n8n workflow builder
Walkthrough
Step 1: Add the HTTP Request node for search
Create an HTTP Request node in your n8n workflow that calls the Scavio API with the caller's question.
JSON
// n8n HTTP Request node configuration:
// Method: POST
// URL: https://api.scavio.dev/api/v1/search
// Authentication: Header Auth
// Header Name: x-api-key
// Header Value: {{ $env.SCAVIO_API_KEY }}
// Body (JSON):
{
"platform": "google",
"query": "{{ $json.caller_query }}"
}Step 2: Parse search results for voice context
Add a Code node that extracts the top 3 snippets and formats them as concise voice-friendly text.
JavaScript
// n8n Code node (JavaScript):
const results = $input.first().json.organic_results || [];
const topResults = results.slice(0, 3).map(r => ({
title: r.title,
snippet: r.snippet || '',
url: r.link
}));
const voiceContext = topResults
.map(r => `${r.title}: ${r.snippet}`)
.join('. ');
return [{ json: { voiceContext, resultCount: topResults.length, results: topResults } }];Step 3: Inject context into the voice agent prompt
Pass the search context to the AI agent node as additional system context for generating the voice response.
Python
// n8n AI Agent node system prompt:
// You are a helpful voice assistant. Use the following live web context
// to answer the caller's question accurately.
//
// Live context: {{ $json.voiceContext }}
//
// Rules:
// - Keep responses under 30 seconds of speech
// - Cite the source if quoting specific data
// - If the context does not answer the question, say so honestly
// Python equivalent for testing the search step:
import requests, os
H = {'x-api-key': os.environ['SCAVIO_API_KEY']}
data = requests.post('https://api.scavio.dev/api/v1/search', headers=H,
json={'platform': 'google', 'query': 'current weather Austin TX'}).json()
snippets = [r.get('snippet', '') for r in data.get('organic_results', [])[:3]]
print(' '.join(snippets))Step 4: Test the end-to-end flow
Trigger a test call and verify the voice agent uses live search data in its response.
Python
# Test via n8n manual execution or webhook:
# 1. Set caller_query to a time-sensitive question
# 2. Run the workflow
# 3. Verify the search node returns results
# 4. Verify the voice context is injected
import requests, os
H = {'x-api-key': os.environ['SCAVIO_API_KEY']}
def test_voice_search(query: str) -> str:
data = requests.post('https://api.scavio.dev/api/v1/search', headers=H,
json={'platform': 'google', 'query': query}, timeout=10).json()
results = data.get('organic_results', [])[:3]
voice_text = '. '.join(r.get('snippet', '') for r in results if r.get('snippet'))
return voice_text[:500]
print(test_voice_search('current weather Austin TX'))Python Example
Python
import requests, os
H = {'x-api-key': os.environ['SCAVIO_API_KEY']}
def voice_context(query):
data = requests.post('https://api.scavio.dev/api/v1/search', headers=H,
json={'platform': 'google', 'query': query}).json()
snippets = [r.get('snippet', '') for r in data.get('organic_results', [])[:3]]
return '. '.join(s for s in snippets if s)
print(voice_context('current weather Austin TX'))JavaScript Example
JavaScript
const H = {'x-api-key': process.env.SCAVIO_API_KEY, 'Content-Type': 'application/json'};
async function voiceContext(query) {
const r = await fetch('https://api.scavio.dev/api/v1/search', {
method: 'POST', headers: H, body: JSON.stringify({platform: 'google', query})
});
const results = (await r.json()).organic_results || [];
return results.slice(0, 3).map(r => r.snippet || '').filter(Boolean).join('. ');
}
voiceContext('current weather Austin TX').then(console.log);Expected Output
JSON
An n8n workflow where the voice agent receives live search context from Scavio before generating each response, enabling real-time answers to caller questions.