Juan Carlos Cavero Gracia This workflow corresponds to n8n.io template #9867 — we link there as the canonical source.
This workflow follows the Agent → Form Trigger 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 →
{
"nodes": [
{
"id": "6d8263d8-298e-48ff-ab17-92c9f4ccb997",
"name": "Download Audio",
"type": "n8n-nodes-base.httpRequest",
"position": [
208,
144
],
"parameters": {
"url": "=https://api.upload-post.com/api/uploadposts/ffmpeg/jobs/{{ $json.job_id }}/download",
"options": {
"response": {
"response": {}
}
},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "5f87dd99-6d60-4c5f-a74c-bfa249153e9e",
"name": "FFmpeg: Extract Audio",
"type": "n8n-nodes-base.httpRequest",
"position": [
-496,
272
],
"parameters": {
"url": "https://api.upload-post.com/api/uploadposts/ffmpeg/jobs/upload",
"method": "POST",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"sendHeaders": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "file",
"parameterType": "formBinaryData",
"inputDataFieldName": "Video"
},
{
"name": "full_command",
"value": "=ffmpeg -y -i {input} -map a:0 -vn -ac 1 -ar 16000 -c:a pcm_s16le {output}"
},
{
"name": "output_extension",
"value": "wav"
}
]
},
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{}
]
}
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "687ed081-a970-4f55-b5ed-047da7ab9217",
"name": "Schedule to TikTok, Instagram, and YouTube",
"type": "n8n-nodes-upload-post.uploadPost",
"position": [
2432,
128
],
"parameters": {
"user": "influencersde",
"title": "={{ $('Parse Gemini Analysis').item.json.video_description_for_tiktok }}",
"video": "data",
"platform": [
"tiktok",
"instagram",
"youtube"
],
"operation": "uploadVideo",
"youtubeTitle": "={{ $('Parse Gemini Analysis').item.json.video_title_for_youtube_short }}",
"scheduledDate": "={{ \n $now\n .setZone('Europe/Madrid')\n .plus({ days: $itemIndex + 1 }) // +1 = empieza ma\u00f1ana\n .set({ hour: 15, minute: 0, second: 0, millisecond: 0 })\n .toFormat('yyyy-LL-dd HH:mm:ss') // si tu nodo acepta este formato\n}}\n",
"instagramTitle": "={{ $('Parse Gemini Analysis').item.json.video_description_for_instagram }}",
"waitForCompletion": "="
},
"credentials": {
"uploadPostApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "0cee305a-553d-45f6-93e4-604f624e6409",
"name": "Parse Whisper Results",
"type": "n8n-nodes-base.code",
"position": [
576,
144
],
"parameters": {
"jsCode": "// Input: item.json.{text, words, duration} del nodo Whisper\nreturn items.map(item => {\n const dur = Number(item.json.duration || 0);\n\n // Redondea a 3 decimales y mantiene tipo number\n const round3 = (n) => Math.round(Number(n) * 1000) / 1000;\n\n const wordsLLM = (item.json.words || []).map(w => ({\n w: w.word,\n s: round3(w.start),\n e: round3(w.end),\n }));\n\n item.json.video_duration = round3(dur);\n item.json.words_llm = wordsLLM; // array limpio para la IA\n item.json.text_llm = item.json.text; // texto tal cual (o l\u00edmpialo si quieres)\n\n return item;\n});\n"
},
"typeVersion": 2
},
{
"id": "afaf8237-f4e5-401f-b6c9-1073d51e274c",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
784,
352
],
"parameters": {
"options": {}
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "2c2b2df2-feec-4454-b178-e1eb7732ee21",
"name": "AI Agent - Select Viral Clips",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
784,
144
],
"parameters": {
"text": "=You are a senior short-form video editor. Read the ENTIRE transcription and word-level timestamps to pick the 3\u201315 MOST VIRAL moments for TikTok/IG Reels/YouTube Shorts. Each clip must be 15\u201360 seconds.\n\n\u26a0\ufe0f FFMPEG TIMING CONTRACT \u2014 HARD REQUIREMENTS:\n- Return timestamps as ABSOLUTE SECONDS from video start (usable in: ffmpeg -ss <start> -to <end> -i <input> \u2026).\n- Numbers ONLY with DOT decimal, up to 3 decimals (examples: 0, 1.250, 17.350).\n- Ensure 0 \u2264 start < end \u2264 VIDEO_DURATION_SECONDS.\n- Each clip 15\u201360s inclusive.\n- Prefer starting 0.2\u20130.4s BEFORE the hook and ending 0.2\u20130.4s AFTER the payoff.\n- Use silent moments for natural cuts; never cut mid-word or mid-phrase.\n- STRICTLY NO time formats other than absolute seconds.\n\nVIDEO_DURATION_SECONDS: {{ $json.video_duration }}\n\nTRANSCRIPT_TEXT (raw):\n{{ JSON.stringify($json.text_llm) }}\n\nWORDS_JSON (array of {w, s, e} where s/e are seconds):\n{{ JSON.stringify($json.words_llm) }}\n\nHARD EXCLUSIONS:\n- No generic intros/outros or sponsor-only segments unless they contain the hook.\n- No clips < 15s or > 60s.\n\nOUTPUT \u2014 RETURN ONLY VALID JSON (no markdown, no comments). Order clips by predicted performance (best first):\n{\n \"shorts\": [\n {\n \"start\": <number seconds, e.g. 12.340>,\n \"end\": <number seconds, e.g. 37.900>,\n \"video_description_for_tiktok\": \"<tiktok video description for get views>\",\n \"video_description_for_instagram\": \"<instagram video description for get views>\",\n \"video_title_for_youtube_short\": \"<youtube short video title for get views>\",\n\n }\n ]\n}\n",
"options": {},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2.2
},
{
"id": "839b4b11-670f-49ad-8bca-7ef00f5e3f86",
"name": "Whisper: Transcribe with Timestamps",
"type": "n8n-nodes-base.httpRequest",
"position": [
384,
144
],
"parameters": {
"url": "https://api.openai.com/v1/audio/transcriptions",
"method": "POST",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"authentication": "predefinedCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "file",
"parameterType": "formBinaryData",
"inputDataFieldName": "data"
},
{
"name": "model",
"value": "whisper-1"
},
{
"name": "response_format",
"value": "verbose_json"
},
{
"name": "timestamp_granularities[]",
"value": "word"
}
]
},
"nodeCredentialType": "openAiApi"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "033d8aea-4f8b-4e71-8ed0-19b56f154909",
"name": "Wait 5s & Retry (Audio)",
"type": "n8n-nodes-base.wait",
"position": [
208,
288
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "4d0ee972-c2a6-418b-aae4-86f12f1d6a44",
"name": "Is Audio Job Completed?",
"type": "n8n-nodes-base.if",
"position": [
32,
272
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "60615090-7a29-4573-9b47-369d6a3e95e9",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.status }}",
"rightValue": "finished"
}
]
}
},
"typeVersion": 2
},
{
"id": "4a63e87e-e81c-4208-9ac6-3d4273bf3fdd",
"name": "Check Audio Job Status",
"type": "n8n-nodes-base.httpRequest",
"position": [
-128,
272
],
"parameters": {
"url": "=https://api.upload-post.com/api/uploadposts/ffmpeg/jobs/{{ $json.job_id }}",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "a9697288-c8a4-498d-9bbd-aa23ab8d85d8",
"name": "Wait 10s (Audio)",
"type": "n8n-nodes-base.wait",
"position": [
-336,
272
],
"parameters": {
"amount": 10
},
"typeVersion": 1.1
},
{
"id": "83b29508-c1d5-4830-9b94-683cc6658b6b",
"name": "Form: Upload Video",
"type": "n8n-nodes-base.formTrigger",
"position": [
-704,
272
],
"parameters": {
"path": "352a575b-42cf-4e9b-8d76-6acec4e40402",
"options": {},
"formTitle": "\ud83c\udfac Video to Viral Shorts",
"formFields": {
"values": [
{
"fieldType": "file",
"fieldLabel": "Video",
"requiredField": true,
"acceptFileTypes": "video/*"
}
]
},
"formDescription": "Upload your video and automatically create viral shorts with AI. Depending on the video's length, 3 to 6 shorts will be generated and automatically scheduled to be uploaded one per day at this time starting tomorrow.\n"
},
"typeVersion": 2.1
},
{
"id": "ed8de4be-df78-4704-9be3-62ce0382b3ba",
"name": "Wait 5s & Retry (Short)",
"type": "n8n-nodes-base.wait",
"position": [
2160,
288
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "48dee67e-3ff8-4e77-8e3c-5ae1af1f0224",
"name": "Download Short",
"type": "n8n-nodes-base.httpRequest",
"position": [
2160,
128
],
"parameters": {
"url": "=https://api.upload-post.com/api/uploadposts/ffmpeg/jobs/{{ $json.job_id }}/download",
"options": {
"response": {
"response": {}
}
},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "894c84ab-4640-4e82-9bd5-3ff286309517",
"name": "Is Short Job Completed?",
"type": "n8n-nodes-base.if",
"position": [
1904,
144
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "60615090-7a29-4573-9b47-369d6a3e95e9",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.status }}",
"rightValue": "finished"
}
]
}
},
"typeVersion": 2
},
{
"id": "63421b85-afea-46e6-a89d-52f8305f2f14",
"name": "Check Short Job Status",
"type": "n8n-nodes-base.httpRequest",
"position": [
1680,
144
],
"parameters": {
"url": "=https://api.upload-post.com/api/uploadposts/ffmpeg/jobs/{{ $json.job_id }}",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "92b26152-a124-4c6d-90f7-50de310733b4",
"name": "Wait 10s (Short)",
"type": "n8n-nodes-base.wait",
"position": [
1472,
144
],
"parameters": {
"amount": 10
},
"typeVersion": 1.1
},
{
"id": "36e8d927-41d9-4fc7-9d62-8a3d41511836",
"name": "Parse Gemini Analysis",
"type": "n8n-nodes-base.code",
"position": [
1088,
144
],
"parameters": {
"jsCode": "// Get Gemini response\nconst data = $input.first().json;\nconst formData = $('Form: Upload Video').first();\n\n// --- Config opcional ---\nconst VIDEO_DURATION_SECONDS =\n Number(formData?.json?.videoDurationSeconds) ||\n Number(formData?.json?.duration) ||\n Number(formData?.json?.meta?.durationSec) ||\n null;\n\n// --- Helpers ---\nconst toMs = (v) => (isFinite(Number(v)) ? Math.round(Number(v) * 1000) : 0);\n\nconst stripCodeFences = (txt) =>\n String(txt || '')\n .replace(/```json\\s*/gi, '')\n .replace(/```\\s*/g, '')\n .trim();\n\nconst extractJsonObject = (txt) => {\n // 1) intenta parse directo\n try { return JSON.parse(txt); } catch {}\n // 2) intenta localizar el primer {...}\n const m = String(txt).match(/\\{[\\s\\S]*\\}/);\n if (m) {\n try { return JSON.parse(m[0]); } catch {}\n }\n throw new Error('No se pudo extraer JSON v\u00e1lido del texto:\\n' + String(txt).slice(0, 300));\n};\n\nconst pickText = (payload) => {\n // Nuevos formatos (string en 'output')\n if (typeof payload === 'string') return payload;\n if (payload?.output) return payload.output;\n\n // Antiguos formatos (content.parts[0].text)\n if (Array.isArray(payload) && payload[0]?.output) return payload[0].output;\n if (Array.isArray(payload) && payload[0]?.content?.parts?.[0]?.text) return payload[0].content.parts[0].text;\n if (payload?.content?.parts?.[0]?.text) return payload.content.parts[0].text;\n\n // Otros\n if (payload?.response) return payload.response;\n if (payload?.text) return payload.text;\n\n // \u00daltimo recurso: stringify\n return JSON.stringify(payload);\n};\n\n// --- 1) Extrae texto crudo del output ---\nlet textResponse = pickText(data);\n\n// --- 2) Limpia fences y parsea el JSON interior ---\ntextResponse = stripCodeFences(textResponse);\nlet parsed = extractJsonObject(textResponse);\n\n// Si vino envuelto otra vez dentro de 'output', vuelve a parsear\nif (!parsed?.shorts && typeof parsed?.output === 'string') {\n parsed = extractJsonObject(stripCodeFences(parsed.output));\n}\n\nconst shorts = Array.isArray(parsed?.shorts) ? parsed.shorts : [];\nif (!shorts.length) {\n throw new Error('Gemini no encontr\u00f3 segmentos interesantes');\n}\n\n// --- 3) Normalizaci\u00f3n opcional (si Gemini mand\u00f3 fracciones 0\u20131 y conocemos D) ---\nconst MIN = 15, MAX = 60;\nconst clamp = (v, lo, hi) => Math.max(lo, Math.min(hi, v));\n\nconst vf = \"scale='min(1080,iw)':'min(1920,ih)':force_original_aspect_ratio=increase,crop=1080:1920,setsar=1\";\n\nreturn shorts.map((s, i) => {\n let startSec = Number(s.start);\n let endSec = Number(s.end);\n\n if (!isFinite(startSec) || !isFinite(endSec)) {\n throw new Error(`Timestamps inv\u00e1lidos en short #${i + 1}`);\n }\n\n // Si parecen porcentajes 0\u20131 y tenemos duraci\u00f3n del v\u00eddeo, convi\u00e9rtelo a segundos\n if (VIDEO_DURATION_SECONDS && endSec <= 1.001) {\n startSec *= VIDEO_DURATION_SECONDS;\n endSec *= VIDEO_DURATION_SECONDS;\n }\n\n // Fuerza rango 15\u201360s de forma suave\n let duration = endSec - startSec;\n if (duration < MIN) endSec = startSec + MIN;\n if (duration > MAX) endSec = startSec + MAX;\n duration = endSec - startSec;\n\n // Mant\u00e9n dentro de la duraci\u00f3n del v\u00eddeo (si la sabemos)\n if (VIDEO_DURATION_SECONDS) {\n startSec = clamp(startSec, 0, Math.max(0, VIDEO_DURATION_SECONDS - MIN));\n endSec = clamp(endSec, startSec + MIN, VIDEO_DURATION_SECONDS);\n duration = endSec - startSec;\n }\n\n // Redondeos\n const start = Number(startSec.toFixed(3));\n const end = Number(endSec.toFixed(3));\n const dur = Number(duration.toFixed(3));\n\n // Construye el comando FFmpeg completo (usa -t = duraci\u00f3n)\n const ffmpegCmd =\n `ffmpeg -y -hide_banner -loglevel error ` +\n `-ss ${start} -t ${dur} -i {input} ` +\n `-c:v h264_nvenc -cq 22 -vf \"${vf}\" ` +\n `-c:a aac -b:a 128k -ar 48000 -ac 2 -movflags +faststart {output}`;\n\n return {\n json: {\n index: i + 1,\n startTime: start,\n endTime: end,\n duration: dur,\n startTimeMs: toMs(start),\n endTimeMs: toMs(end),\n durationMs: toMs(dur),\n video_description_for_tiktok: s.video_description_for_tiktok ?? '',\n video_description_for_instagram: s.video_description_for_instagram ?? '',\n video_title_for_youtube_short: s.video_title_for_youtube_short ?? '',\n full_command: ffmpegCmd\n },\n binary: formData.binary\n };\n});\n"
},
"typeVersion": 2
},
{
"id": "20a0553c-352c-4903-bd33-2216c7f6accf",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-752,
-464
],
"parameters": {
"color": 7,
"width": 480,
"height": 592,
"content": "**AUTO-SHORTS GENERATOR**\n\n**How it Works:**\n1. Upload a long video via the form.\n2. AI transcribes the audio (Whisper) and finds the most viral clips (Gemini).\n3. The clips are auto-cut, cropped, and prepared for social media.\n4. Shorts are scheduled to post daily on TikTok, Instagram, and YouTube.\n\n**Quick Setup:**\n1. **OpenAI Whisper:** Add your API key to the `Whisper: Transcribe` node.\n2. **Google Gemini:** Add your Google AI Studio API key to the `Google Gemini Chat Model` node.\n3. **Upload-Post:**\n * Sign up at `app.upload-post.com` & connect your social accounts.\n * Generate an API token.\n * In n8n, create credentials for the `HTTP Request` nodes (Header Auth) and the `Schedule...` node (Upload-Post API) using that token.\n4. **Scheduling:** Adjust the post time and timezone in the `Schedule to...` node.\n5. **To Run:** Use the URL from the `Form: Upload Video` node to upload your video."
},
"typeVersion": 1
},
{
"id": "d17e4d15-bd41-460d-8739-0f423e70efd9",
"name": "FFmpeg: Upload & Cut",
"type": "n8n-nodes-base.httpRequest",
"position": [
1264,
144
],
"parameters": {
"url": "https://api.upload-post.com/api/uploadposts/ffmpeg/jobs/upload",
"method": "POST",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "file",
"parameterType": "formBinaryData",
"inputDataFieldName": "Video"
},
{
"name": "full_command",
"value": "=ffmpeg -y -hide_banner -loglevel error -ss {{ $json.startTime }} -t {{ $json.duration }} -i {input} -vf \"scale=trunc(iw/2)*2:trunc(ih/2)*2,setsar=1\" -c:v h264_nvenc -cq 22 -pix_fmt yuv420p -c:a aac -b:a 128k -ar 48000 -ac 2 -movflags +faststart {output}"
},
{
"name": "output_extension",
"value": "mp4"
}
]
},
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "abfbf025-e4b1-498c-8cbc-990d4b923bf2",
"name": "Section: Intake & Form",
"type": "n8n-nodes-base.stickyNote",
"position": [
-752,
128
],
"parameters": {
"width": 228,
"height": 352,
"content": "**Intake & Form**\n- Form: Upload Video"
},
"typeVersion": 1
},
{
"id": "e99945ee-8a4f-4eaa-b835-def0a25f31d9",
"name": "Section: Transcription & Parsing",
"type": "n8n-nodes-base.stickyNote",
"position": [
352,
16
],
"parameters": {
"width": 428,
"height": 320,
"content": "**Transcription & Parsing**\n- Whisper: Transcribe with Timestamps\n- Parse Whisper Results\n- Download Audio"
},
"typeVersion": 1
},
{
"id": "1b8fe57b-93a8-4e42-bfbf-920a8c9ba9a5",
"name": "Section: AI Selection (Gemini)",
"type": "n8n-nodes-base.stickyNote",
"position": [
768,
16
],
"parameters": {
"width": 420,
"height": 480,
"content": "**AI Selection**\n- Google Gemini Chat Model\n- AI Agent \u2013 Select Viral Clips\n- Parse Gemini Analysis"
},
"typeVersion": 1
},
{
"id": "ab0e8e1b-252a-44d6-a355-e1e1306776fb",
"name": "Section: FFmpeg Audio Job Loop",
"type": "n8n-nodes-base.stickyNote",
"position": [
-528,
128
],
"parameters": {
"width": 880,
"height": 352,
"content": "**FFmpeg Audio Job Loop**\n- FFmpeg: Extract Audio\n- Wait 10s (Audio) \u2192 Check Audio Job Status \u2192 Is Audio Job Completed?\n- Retry path: Wait 5s & Retry (Audio)"
},
"typeVersion": 1
},
{
"id": "00d1a683-0c3f-4184-b9f5-dc0f120c85df",
"name": "Section: FFmpeg Short Job Loop",
"type": "n8n-nodes-base.stickyNote",
"position": [
1184,
16
],
"parameters": {
"width": 1132,
"height": 480,
"content": "**FFmpeg Short Job Loop**\n- FFmpeg: Upload & Cut\n- Wait 10s (Short) \u2192 Check Short Job Status \u2192 Is Short Job Completed?\n- Retry path: Wait 5s & Retry (Short)"
},
"typeVersion": 1
},
{
"id": "0c6292f9-b1db-4710-8b10-1a7de6d609ad",
"name": "Section: Scheduling",
"type": "n8n-nodes-base.stickyNote",
"position": [
2320,
16
],
"parameters": {
"width": 420,
"height": 480,
"content": "**Scheduling**\n- Download Short\n- Schedule to TikTok, Instagram, and YouTube"
},
"typeVersion": 1
}
],
"connections": {
"Download Audio": {
"main": [
[
{
"node": "Whisper: Transcribe with Timestamps",
"type": "main",
"index": 0
}
]
]
},
"Download Short": {
"main": [
[
{
"node": "Schedule to TikTok, Instagram, and YouTube",
"type": "main",
"index": 0
}
]
]
},
"Wait 10s (Audio)": {
"main": [
[
{
"node": "Check Audio Job Status",
"type": "main",
"index": 0
}
]
]
},
"Wait 10s (Short)": {
"main": [
[
{
"node": "Check Short Job Status",
"type": "main",
"index": 0
}
]
]
},
"Form: Upload Video": {
"main": [
[
{
"node": "FFmpeg: Extract Audio",
"type": "main",
"index": 0
}
]
]
},
"FFmpeg: Upload & Cut": {
"main": [
[
{
"node": "Wait 10s (Short)",
"type": "main",
"index": 0
}
]
]
},
"FFmpeg: Extract Audio": {
"main": [
[
{
"node": "Wait 10s (Audio)",
"type": "main",
"index": 0
}
]
]
},
"Parse Gemini Analysis": {
"main": [
[
{
"node": "FFmpeg: Upload & Cut",
"type": "main",
"index": 0
}
]
]
},
"Parse Whisper Results": {
"main": [
[
{
"node": "AI Agent - Select Viral Clips",
"type": "main",
"index": 0
}
]
]
},
"Check Audio Job Status": {
"main": [
[
{
"node": "Is Audio Job Completed?",
"type": "main",
"index": 0
}
]
]
},
"Check Short Job Status": {
"main": [
[
{
"node": "Is Short Job Completed?",
"type": "main",
"index": 0
}
]
]
},
"Is Audio Job Completed?": {
"main": [
[
{
"node": "Download Audio",
"type": "main",
"index": 0
}
],
[
{
"node": "Wait 5s & Retry (Audio)",
"type": "main",
"index": 0
}
]
]
},
"Is Short Job Completed?": {
"main": [
[
{
"node": "Download Short",
"type": "main",
"index": 0
}
],
[
{
"node": "Wait 5s & Retry (Short)",
"type": "main",
"index": 0
}
]
]
},
"Wait 5s & Retry (Audio)": {
"main": [
[
{
"node": "Check Audio Job Status",
"type": "main",
"index": 0
}
]
]
},
"Wait 5s & Retry (Short)": {
"main": [
[
{
"node": "Check Short Job Status",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent - Select Viral Clips",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"AI Agent - Select Viral Clips": {
"main": [
[
{
"node": "Parse Gemini Analysis",
"type": "main",
"index": 0
}
]
]
},
"Whisper: Transcribe with Timestamps": {
"main": [
[
{
"node": "Parse Whisper Results",
"type": "main",
"index": 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.
googlePalmApihttpHeaderAuthopenAiApiuploadPostApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This automation template turns any long video into multiple viral-ready short clips and auto-schedules them to TikTok, Instagram Reels, and YouTube Shorts. It works with both vertical and horizontal inputs and respects the original input resolution (no unnecessary upscaling),…
Source: https://n8n.io/workflows/9867/ — 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.
This automated workflow template transforms a single product image into a complete professional advertisement video with dynamic motion and custom soundtrack. Perfect for e-commerce businesses, market
HTTP Request, Output Parser Structured, Tool Think +4
This automation workflow is designed for e-commerce businesses, digital marketers, and entrepreneurs who need to create high-quality promotional content for their products quickly and efficiently. Fro
Output Parser Structured, Tool Think, Agent +5
How it Works
Memory Buffer Window, Agent, Output Parser Structured +9
This is an automated blog post generation system that: Researches topics using AI agents and web search tools Writes complete blog posts with proper SEO structure Generates custom images for each post
Output Parser Structured, Google Gemini Chat, HTTP Request Tool +11
This workflow is designed for e-commerce, marketing teams, or creators who want to automate the production of high-quality, AI-generated product visuals and ad creatives.
HTTP Request, Error Trigger, Discord +7