Transcription audio IA et générateur de rapports Google Docs

Intermédiaire

Ceci est unAIworkflow d'automatisation du domainecontenant 9 nœuds.Utilise principalement des nœuds comme Webhook, GoogleDocs, GmailTrigger, VlmRun, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. Transcription audio et générateur de rapports Google Docs

Prérequis
  • Point de terminaison HTTP Webhook (généré automatiquement par n8n)
  • Compte Google et informations d'identification Gmail API
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
  "meta": {
    "instanceId": "0a7ae129a7d703150135f6cc24d0469f20ffd22b5ed59c23ee3e0608264e6d98",
    "templateId": "3905",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "2175eca1-4842-4601-b0ac-84264cdc48ca",
      "name": "🎙️ Vue d'ensemble du workflow",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -260,
        720
      ],
      "parameters": {
        "color": 7,
        "width": 460,
        "height": 720,
        "content": "## 🎙️ AI Audio Transcription with VLM Run\n\n**Overview:**\nAutomatically transcribes audio files from Gmail and generates formatted transcription reports in Google Docs.\n\n**Workflow:**\n1. 📧 Monitor Gmail for audio attachments\n2. 🎵 Extract and process audio files\n3. 🤖 Transcribe using VLM Run AI\n4. 🔗 Receive results via webhook\n5. 📄 Generate formatted Google Doc\n\n\n**Perfect for:**\n- Meeting recordings\n- Voice memos\n- Interview transcriptions\n- Podcast notes\n- Audio journalism\n- Accessibility documentation\n\n\n**Requirements:**\n- VLM Run API access\n- Gmail OAuth2\n- Google Docs OAuth2\n- Webhook endpoint"
      },
      "typeVersion": 1
    },
    {
      "id": "3d1b367c-226c-4d9c-bc9e-0643ff3896bc",
      "name": "📧 Surveillance des emails",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        220,
        720
      ],
      "parameters": {
        "color": 7,
        "width": 360,
        "height": 720,
        "content": "## 📧 Gmail Audio Detection\n\n**Monitors incoming emails and automatically downloads audio attachments.**\n\n**Process:**\n1. Polls Gmail every minute\n2. Detects new emails with attachments\n3. Downloads audio files automatically\n4. Triggers transcription workflow\n\n\n**Supported Formats:**\n- MP3, WAV, M4A\n- AAC, OGG, FLAC\n- Various bitrates\n- Mobile recordings\n\n\n**Configuration:**\n- Enable attachment downloads\n- Automatic file extraction"
      },
      "typeVersion": 1
    },
    {
      "id": "4c2744d9-c35d-4629-ac54-b3f299cf16e3",
      "name": "🤖 Transcription par IA",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        600,
        720
      ],
      "parameters": {
        "color": 2,
        "width": 360,
        "height": 720,
        "content": "## 🤖 Audio AI Processing\n\n**VLM Run transcribes audio with high accuracy**\n\n**Features:**\n- Advanced speech recognition\n- Automatic punctuation\n- Timestamp generation\n\n\n**Output:**\n- Complete transcription\n- Time-segmented text\n- Metadata extraction\n- Duration information\n\n\n**Benefits:**\n- Human-level accuracy\n- Fast processing\n- Consistent formatting\n- Professional quality"
      },
      "typeVersion": 1
    },
    {
      "id": "52c19808-27ae-4ccd-af4d-a977bd44f18a",
      "name": "🔗 Traitement asynchrone",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        980,
        720
      ],
      "parameters": {
        "color": 5,
        "width": 320,
        "height": 720,
        "content": "## 🔗 Webhook Processing Flow\n\n**How asynchronous transcription works:**\n\n**Step 1:** Audio sent to VLM Run with callback URL\n**Step 2:** Transcription starts in background\n**Step 3:** Webhook receives completion\n**Step 4:** Results formatted for Google Docs\n\n\n**Why Async?**\n- Handles long audio files\n- Prevents workflow timeouts\n- Better resource management\n- Reliable processing\n\n\n**Callback Data:**\n- Complete transcript\n- Segment timestamps\n- Processing metadata\n- Error handling"
      },
      "typeVersion": 1
    },
    {
      "id": "7046634c-3534-4f62-9df9-7ece42a4b969",
      "name": "📄 Génération de document",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1320,
        720
      ],
      "parameters": {
        "color": 7,
        "width": 320,
        "height": 720,
        "content": "## 📄 Professional Reports\n\n**Creates beautifully formatted Google Docs with transcription results.**\n\n**Report includes:**\n- Date and timestamp\n- Total audio duration\n- Segmented transcription\n- Time markers for each segment\n- Professional formatting\n\n\n**Output Location:**\n- Specified Google Doc\n- Appends new transcriptions\n- Maintains formatting"
      },
      "typeVersion": 1
    },
    {
      "id": "31d1f0c3-73e7-4e1a-bc08-72c5694e7153",
      "name": "Surveiller les pièces jointes des emails",
      "type": "n8n-nodes-base.gmailTrigger",
      "notes": "Continuously monitors Gmail for new emails with audio attachments. Automatically downloads all attachments and triggers the transcription workflow.",
      "position": [
        320,
        1260
      ],
      "parameters": {
        "simple": false,
        "filters": {},
        "options": {
          "downloadAttachments": true
        },
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        }
      },
      "credentials": {
        "gmailOAuth2": {
          "id": "7MVziRpoyD8arghO",
          "name": "Gmail account 2"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "d2c14402-db05-4bf4-a8a5-402587d69ee8",
      "name": "Exécuter le transcripteur audio VLM",
      "type": "@vlm-run/n8n-nodes-vlmrun.vlmRun",
      "notes": "Processes audio files using VLM AI to generate accurate transcriptions with timestamps. Runs asynchronously for large audio files.",
      "position": [
        720,
        1260
      ],
      "parameters": {
        "file": "attachment_0",
        "domain": "audio.transcription",
        "operation": "audio",
        "callbackUrl": "https://playground.vlm.run/webhook/audio-transcription",
        "processAsynchronously": true
      },
      "credentials": {
        "vlmRunApi": {
          "id": "cF5KpbVmnt36bdWr",
          "name": "VLM Run account 6"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "98e98532-dc44-4b15-a75d-24b3d7823c84",
      "name": "Recevoir les résultats de transcription",
      "type": "n8n-nodes-base.webhook",
      "notes": "Receives the completed transcription from VLM AI when asynchronous processing is finished. Contains full transcript with timestamps.",
      "position": [
        1080,
        1260
      ],
      "webhookId": "d599acd8-1891-4d07-b2f9-092cb6381b41",
      "parameters": {
        "path": "audio-transcription",
        "options": {},
        "httpMethod": "POST"
      },
      "typeVersion": 2
    },
    {
      "id": "c9468f04-42da-4725-a462-97cdcf6c40ac",
      "name": "Générer le rapport de transcription",
      "type": "n8n-nodes-base.googleDocs",
      "notes": "Creates a professionally formatted Google Doc with the transcription results, including timestamps and metadata.",
      "position": [
        1420,
        1260
      ],
      "parameters": {
        "simple": false,
        "actionsUi": {
          "actionFields": [
            {
              "text": "=📄 Audio Transcription Report\n\n🗓️ Date: {{ new Date($json.body.completed_at).toLocaleString('en-US', { dateStyle: 'medium', timeStyle: 'short' }) }}  \n⏱️ Total Duration: {{ $json.body.response.metadata.duration }} seconds  \n{{ \n$json.body.response.segments.map((segment, index) => \n  `\\n` +\n  `🔹 Segment ${index + 1}\\n` +\n  `⏰ Time: ${segment.start_time.toFixed(2)}s → ${segment.end_time.toFixed(2)}s\\n` +\n  `📝 Transcript: \"${segment.content.trim()}\"\\n`\n).join('\\n')\n}}\n",
              "action": "insert"
            }
          ]
        },
        "operation": "update",
        "documentURL": "https://docs.google.com/document/d/1QFHvOgEYKMLVpIRv6Mc7lXfDXhtoozgEK7O-wuNLzl0/edit?tab=t.0",
        "authentication": "oAuth2"
      },
      "credentials": {
        "googleDocsOAuth2Api": {
          "id": "3x0WI9iZ6ToA2fXw",
          "name": "Google Docs account"
        }
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "31d1f0c3-73e7-4e1a-bc08-72c5694e7153": {
      "main": [
        [
          {
            "node": "d2c14402-db05-4bf4-a8a5-402587d69ee8",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "98e98532-dc44-4b15-a75d-24b3d7823c84": {
      "main": [
        [
          {
            "node": "c9468f04-42da-4725-a462-97cdcf6c40ac",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
Foire aux questions

Comment utiliser ce workflow ?

Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.

Dans quelles scénarios ce workflow est-il adapté ?

Intermédiaire - Intelligence Artificielle

Est-ce payant ?

Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.

Informations sur le workflow
Niveau de difficulté
Intermédiaire
Nombre de nœuds9
Catégorie1
Types de nœuds5
Description de la difficulté

Adapté aux utilisateurs expérimentés, avec des workflows de complexité moyenne contenant 6-15 nœuds

Auteur
Shahrear

Shahrear

@shahrear

I’m Shahrear, a Software Engineer with over 5 years of experience in full-stack development and workflow automation. I specialize in building intelligent, scalable automations using n8n, helping teams streamline operations and boost productivity. I’m also an expert in developing custom n8n nodes, with published work on npm - including the @vlm-run/n8n-nodes-vlmrun package. https://github.com/vlm-run/n8n-nodes-vlmrun

Liens externes
Voir sur n8n.io

Partager ce workflow

Catégories

Catégories: 34