This workflow follows the HTTP Request → Postgres recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "Real-time Voice AI Analytics",
"nodes": [
{
"parameters": {
"rule": {
"interval": [
{
"field": "seconds",
"secondsInterval": 30
}
]
}
},
"id": "analytics-trigger-001",
"name": "Analytics Collection Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
240,
300
]
},
{
"parameters": {
"operation": "executeQuery",
"query": "SELECT * FROM voice_interactions_v2 WHERE created_at > NOW() - INTERVAL '30 seconds' LIMIT 1000;",
"options": {}
},
"id": "recent-interactions-002",
"name": "Get Recent Interactions",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
460,
300
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"language": "javaScript",
"jsCode": "// Calculate real-time metrics\nconst interactions = $input.all().map(item => item.json);\nconst now = new Date();\nconst thirtySecondsAgo = new Date(now.getTime() - 30000);\n\n// Performance metrics\nconst totalInteractions = interactions.length;\nconst avgProcessingTime = interactions.reduce((sum, i) => sum + (i.processing_metrics?.total_time || 0), 0) / Math.max(totalInteractions, 1);\nconst avgConfidence = interactions.reduce((sum, i) => sum + (i.processing_metrics?.stt_confidence || 0), 0) / Math.max(totalInteractions, 1);\n\n// Language distribution\nconst languageStats = {};\ninteractions.forEach(i => {\n const lang = i.processing_metrics?.language || 'unknown';\n languageStats[lang] = (languageStats[lang] || 0) + 1;\n});\n\n// Model usage statistics\nconst modelStats = {};\ninteractions.forEach(i => {\n const model = i.processing_metrics?.llm_model || 'unknown';\n modelStats[model] = (modelStats[model] || 0) + 1;\n});\n\n// Quality metrics\nconst qualityMetrics = {\n high_confidence: interactions.filter(i => (i.processing_metrics?.stt_confidence || 0) > 0.9).length,\n medium_confidence: interactions.filter(i => {\n const conf = i.processing_metrics?.stt_confidence || 0;\n return conf >= 0.7 && conf <= 0.9;\n }).length,\n low_confidence: interactions.filter(i => (i.processing_metrics?.stt_confidence || 0) < 0.7).length\n};\n\n// Error tracking\nconst errors = interactions.filter(i => i.processing_metrics?.errors || i.status === 'error').length;\nconst errorRate = totalInteractions > 0 ? (errors / totalInteractions) * 100 : 0;\n\n// User satisfaction (if available)\nconst ratingsData = interactions.filter(i => i.user_feedback?.rating);\nconst avgRating = ratingsData.length > 0 ? \n ratingsData.reduce((sum, i) => sum + i.user_feedback.rating, 0) / ratingsData.length : null;\n\n// Response time distribution\nconst responseTimeBuckets = {\n fast: interactions.filter(i => (i.processing_metrics?.total_time || 0) < 1000).length, // < 1s\n medium: interactions.filter(i => {\n const time = i.processing_metrics?.total_time || 0;\n return time >= 1000 && time < 3000;\n }).length, // 1-3s\n slow: interactions.filter(i => (i.processing_metrics?.total_time || 0) >= 3000).length // > 3s\n};\n\n// Feature usage\nconst featureUsage = {\n rag_used: interactions.filter(i => i.processing_metrics?.rag_used).length,\n voice_activity_detected: interactions.filter(i => i.processing_metrics?.vad_confidence > 0.5).length,\n multi_language: Object.keys(languageStats).length\n};\n\nconst analytics = {\n timestamp: now.toISOString(),\n timeWindow: '30s',\n performance: {\n totalInteractions,\n avgProcessingTime: Math.round(avgProcessingTime),\n avgConfidence: Math.round(avgConfidence * 100) / 100,\n errorRate: Math.round(errorRate * 100) / 100,\n throughput: Math.round((totalInteractions / 30) * 100) / 100 // interactions per second\n },\n quality: {\n ...qualityMetrics,\n avgRating,\n ratingsCount: ratingsData.length\n },\n distribution: {\n languages: languageStats,\n models: modelStats,\n responseTimes: responseTimeBuckets\n },\n features: featureUsage\n};\n\nreturn { json: analytics };"
},
"id": "calculate-metrics-003",
"name": "Calculate Real-time Metrics",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
680,
300
]
},
{
"parameters": {
"method": "POST",
"url": "http://prometheus:9090/api/v1/write",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "text/plain"
}
]
},
"sendBody": true,
"bodyContentType": "raw",
"body": "=# Voice AI Metrics\n# Performance\nvoice_ai_interactions_total {{ $json.performance.totalInteractions }} {{ Date.now() }}\nvoice_ai_avg_processing_time_ms {{ $json.performance.avgProcessingTime }} {{ Date.now() }}\nvoice_ai_avg_confidence {{ $json.performance.avgConfidence }} {{ Date.now() }}\nvoice_ai_error_rate_percent {{ $json.performance.errorRate }} {{ Date.now() }}\nvoice_ai_throughput_per_second {{ $json.performance.throughput }} {{ Date.now() }}\n\n# Quality\nvoice_ai_high_confidence_interactions {{ $json.quality.high_confidence }} {{ Date.now() }}\nvoice_ai_medium_confidence_interactions {{ $json.quality.medium_confidence }} {{ Date.now() }}\nvoice_ai_low_confidence_interactions {{ $json.quality.low_confidence }} {{ Date.now() }}\n{{ $json.quality.avgRating ? `voice_ai_avg_rating ${$json.quality.avgRating} ${Date.now()}` : '' }}\n\n# Features\nvoice_ai_rag_usage {{ $json.features.rag_used }} {{ Date.now() }}\nvoice_ai_vad_detections {{ $json.features.voice_activity_detected }} {{ Date.now() }}\nvoice_ai_languages_used {{ $json.features.multi_language }} {{ Date.now() }}\n\n# Response Times\nvoice_ai_fast_responses {{ $json.distribution.responseTimes.fast }} {{ Date.now() }}\nvoice_ai_medium_responses {{ $json.distribution.responseTimes.medium }} {{ Date.now() }}\nvoice_ai_slow_responses {{ $json.distribution.responseTimes.slow }} {{ Date.now() }}",
"options": {
"timeout": 5000
}
},
"id": "push-to-prometheus-004",
"name": "Push Metrics to Prometheus",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
900,
300
],
"continueOnFail": true
},
{
"parameters": {
"operation": "executeQuery",
"query": "INSERT INTO analytics_snapshots (timestamp, time_window, metrics_data, total_interactions, avg_processing_time, error_rate, avg_confidence) VALUES ($1, $2, $3, $4, $5, $6, $7)",
"options": {
"queryParameters": "={{ $json.timestamp }},{{ $json.timeWindow }},{{ JSON.stringify($json) }},{{ $json.performance.totalInteractions }},{{ $json.performance.avgProcessingTime }},{{ $json.performance.errorRate }},{{ $json.performance.avgConfidence }}"
}
},
"id": "store-analytics-005",
"name": "Store Analytics Snapshot",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
1120,
300
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"continueOnFail": true
},
{
"parameters": {
"conditions": {
"string": [
{
"value1": "={{ $json.performance.errorRate > 5.0 || $json.performance.avgConfidence < 0.8 || $json.performance.avgProcessingTime > 3000 }}",
"operation": "equal",
"value2": "true"
}
]
}
},
"id": "check-alerts-006",
"name": "Check Alert Conditions",
"type": "n8n-nodes-base.if",
"typeVersion": 1,
"position": [
1340,
300
]
},
{
"parameters": {
"method": "POST",
"url": "={{ $vars.SLACK_WEBHOOK_URL }}",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"bodyContentType": "json",
"jsonBody": "={\n \"text\": \"\ud83d\udea8 Voice AI Alert Triggered\",\n \"blocks\": [\n {\n \"type\": \"header\",\n \"text\": {\n \"type\": \"plain_text\",\n \"text\": \"Voice AI Performance Alert\"\n }\n },\n {\n \"type\": \"section\",\n \"text\": {\n \"type\": \"mrkdwn\",\n \"text\": \"*Performance Issues Detected*\\n\\n\u2022 Error Rate: {{ $('Calculate Real-time Metrics').item.json.performance.errorRate }}%\\n\u2022 Avg Confidence: {{ $('Calculate Real-time Metrics').item.json.performance.avgConfidence }}\\n\u2022 Avg Processing Time: {{ $('Calculate Real-time Metrics').item.json.performance.avgProcessingTime }}ms\\n\u2022 Total Interactions: {{ $('Calculate Real-time Metrics').item.json.performance.totalInteractions }}\\n\\n*Time:* {{ $('Calculate Real-time Metrics').item.json.timestamp }}\"\n }\n },\n {\n \"type\": \"actions\",\n \"elements\": [\n {\n \"type\": \"button\",\n \"text\": {\n \"type\": \"plain_text\",\n \"text\": \"View Dashboard\"\n },\n \"url\": \"http://grafana:3000/d/voice-ai-overview\"\n }\n ]\n }\n ]\n}"
},
"id": "send-alert-007",
"name": "Send Alert Notification",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1560,
240
],
"continueOnFail": true
}
],
"connections": {
"Analytics Collection Trigger": {
"main": [
[
{
"node": "Get Recent Interactions",
"type": "main",
"index": 0
}
]
]
},
"Get Recent Interactions": {
"main": [
[
{
"node": "Calculate Real-time Metrics",
"type": "main",
"index": 0
}
]
]
},
"Calculate Real-time Metrics": {
"main": [
[
{
"node": "Push Metrics to Prometheus",
"type": "main",
"index": 0
},
{
"node": "Store Analytics Snapshot",
"type": "main",
"index": 0
},
{
"node": "Check Alert Conditions",
"type": "main",
"index": 0
}
]
]
},
"Check Alert Conditions": {
"main": [
[
{
"node": "Send Alert Notification",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1",
"saveManualExecutions": false
},
"staticData": null,
"tags": [
"analytics",
"monitoring",
"real-time"
],
"triggerCount": 1,
"updatedAt": "2025-06-27T00:00:00.000Z",
"versionId": "1.0"
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
postgres
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Real-time Voice AI Analytics. Uses postgres, httpRequest. Scheduled trigger; 7 nodes.
Source: https://github.com/161sam/n8n-voice-ai/blob/main/workflows/Real-time-Voice-AI-Analytics.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Disparador 1.8. Uses itemLists, postgres, emailSend, httpRequest. Scheduled trigger; 85 nodes.
Item Lists, Postgres, Email Send +1
공유회_알림톡_크론. Uses postgres, httpRequest, n8n-nodes-solapi. Scheduled trigger; 39 nodes.
Postgres, HTTP Request, N8N Nodes Solapi
QuepasaAutomatic. Uses postgres, postgresTrigger, httpRequest. Scheduled trigger; 39 nodes.
Postgres, Postgres Trigger, HTTP Request
QuepasaAutomatic. Uses postgres, postgresTrigger, httpRequest. Scheduled trigger; 39 nodes.
Postgres, Postgres Trigger, HTTP Request
QuepasaAutomatic. Uses postgres, postgresTrigger, httpRequest. Scheduled trigger; 39 nodes.
Postgres, Postgres Trigger, HTTP Request