deAPI Team This workflow corresponds to n8n.io template #14662 — we link there as the canonical source.
This workflow follows the Agent → Anthropic Chat 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Multilingual Video Localization",
"tags": [],
"nodes": [
{
"id": "5a7d171d-f9f3-4a92-ad0e-4f4bea085d2c",
"name": "Sticky Note - Overview",
"type": "n8n-nodes-base.stickyNote",
"position": [
1360,
880
],
"parameters": {
"width": 668,
"height": 960,
"content": "## Try It Out!\n### Localize a spokesperson video into another language with a new presenter \u2014 no filming required.\n\nThis workflow transcribes a video, translates the speech, generates dubbed audio, creates a lip-synced video.\n\n### How it works\n1. **Manual Trigger** starts the workflow\n2. **Set Fields** defines the target language\n3. **Read Source Video** and **Read Local Presenter Image** load the input files in parallel\n4. **deAPI Transcribe Video** extracts the original speech as text with timestamps\n5. **AI Agent** translates the transcript into the target language\n6. **deAPI Generate Speech** creates dubbed audio in the target language\n7. **deAPI Generate From Audio** produces a lip-synced talking-head video from the dubbed audio, using the local presenter image as the first frame\n\n### Requirements\n- [deAPI](https://deapi.ai) account for transcription, TTS, video generation\n- Anthropic account for the AI Agent (translation)\n- A spokesperson video\n- A reference image of the local presenter\n- n8n instance must be on **HTTPS**\n\n### Need Help?\nJoin the [n8n Discord](https://discord.gg/n8n) or ask in the [Forum](https://community.n8n.io/)!\n\nHappy Automating!"
},
"typeVersion": 1
},
{
"id": "4845a8b4-833f-40b4-a819-306e59b27d13",
"name": "Sticky Note - Example",
"type": "n8n-nodes-base.stickyNote",
"position": [
-64,
1888
],
"parameters": {
"color": 6,
"width": 380,
"height": 400,
"content": "### Example Input\n\n**Source Video:**\nAn 8-second clip of a presenter speaking in English\n\n**Local Presenter Image:**\nA photo of the person who should appear in the localized video\n\n**Target Language:**\nSpanish"
},
"typeVersion": 1
},
{
"id": "7a3b16f3-4445-49b7-968e-c80368a31265",
"name": "Sticky Note - Trigger",
"type": "n8n-nodes-base.stickyNote",
"position": [
352,
1888
],
"parameters": {
"color": 7,
"width": 400,
"height": 460,
"content": "## 1. Start & Configure\nClick **Test Workflow** to run.\n\nThe **Set Fields** node defines:\n- **target_language** \u2014 the language for the localized video (e.g. Spanish, Japanese, French)"
},
"typeVersion": 1
},
{
"id": "6940f5b8-44b6-4249-bd6c-d33240ef2758",
"name": "Sticky Note - Read Files",
"type": "n8n-nodes-base.stickyNote",
"position": [
784,
1712
],
"parameters": {
"color": 7,
"width": 452,
"height": 764,
"content": "## 2. Load Files\nReads both input files in parallel:\n\n**Source Video** (top branch)\n- Output field: `video`\n- The original spokesperson video\n- Formats: MP4, MPEG, MOV, AVI, WMV, OGG\n\n**Local Presenter Image** (bottom branch)\n- Output field: `image`\n- Reference photo of the local presenter\n- Formats: JPG, JPEG, PNG, GIF, BMP, WebP\n- Max size: 10 MB\n\nUpdate the **File Path** in each node."
},
"typeVersion": 1
},
{
"id": "f34468c8-4e5b-4f2c-8c71-04422f1add7f",
"name": "Sticky Note - Transcribe",
"type": "n8n-nodes-base.stickyNote",
"position": [
1280,
1888
],
"parameters": {
"color": 7,
"width": 424,
"height": 476,
"content": "## 3. Transcribe\n[deAPI Documentation](https://docs.deapi.ai)\n\n**Transcribe Video** uses **Whisper Large V3** to extract the spoken text from the video.\n\nTimestamps are included so the AI can preserve pacing during translation."
},
"typeVersion": 1
},
{
"id": "dc61ce3a-0ed5-4f2f-8642-529c58eb5ef8",
"name": "Sticky Note - Translate",
"type": "n8n-nodes-base.stickyNote",
"position": [
1744,
1888
],
"parameters": {
"color": 7,
"width": 400,
"height": 540,
"content": "## 4. Translate\nThe **AI Agent** translates the transcript into the target language.\n\nIt preserves the natural tone and pacing of the original speech, adapting idioms and cultural references for the target audience."
},
"typeVersion": 1
},
{
"id": "6477e3df-490a-4a37-8b9c-9a6e8c5d11ad",
"name": "Sticky Note - TTS",
"type": "n8n-nodes-base.stickyNote",
"position": [
2176,
1888
],
"parameters": {
"color": 7,
"width": 400,
"height": 492,
"content": "## 5. Generate Dubbed Speech\n[deAPI Documentation](https://docs.deapi.ai)\n\n**Generate Speech** uses **Qwen3** to create natural-sounding speech from the translated text.\n\nSwap for **Clone a Voice** to preserve the original speaker's voice characteristics."
},
"typeVersion": 1
},
{
"id": "af9b5122-2305-4803-880d-efaa7bfc28de",
"name": "Sticky Note - Audio to Video",
"type": "n8n-nodes-base.stickyNote",
"position": [
2608,
1888
],
"parameters": {
"color": 7,
"width": 528,
"height": 588,
"content": "## 6. Generate Lip-Synced Video\n[deAPI Documentation](https://docs.deapi.ai)\n\n**Generate From Audio** uses **LTX-2.3 22B** to create a talking-head video synced to the dubbed speech.\n\nThe local presenter image is used as the first frame to guide the visual appearance."
},
"typeVersion": 1
},
{
"id": "c1a91124-f87e-43fe-bd88-74ff43a00a7b",
"name": "Manual Trigger",
"type": "n8n-nodes-base.manualTrigger",
"position": [
384,
2192
],
"parameters": {},
"typeVersion": 1
},
{
"id": "f12fc28b-b55d-4b9e-b3f9-059751d56012",
"name": "Set Fields",
"type": "n8n-nodes-base.set",
"position": [
608,
2192
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "field-target-language",
"name": "target_language",
"type": "string",
"value": "Spanish"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "d13bdc81-57a2-4a9d-be84-76826691d664",
"name": "Read Source Video",
"type": "n8n-nodes-base.readWriteFile",
"position": [
960,
2096
],
"parameters": {
"options": {
"dataPropertyName": "video"
},
"fileSelector": "/path/to/your/spokesperson-video.mp4"
},
"typeVersion": 1
},
{
"id": "6ef5ce65-2131-4608-b307-17459c0f7ce7",
"name": "Read Local Presenter Image",
"type": "n8n-nodes-base.readWriteFile",
"position": [
960,
2288
],
"parameters": {
"options": {
"dataPropertyName": "image"
},
"fileSelector": "/path/to/your/local-presenter.jpg"
},
"typeVersion": 1
},
{
"id": "baccfe84-3b58-439e-816a-7602083bd603",
"name": "deAPI Transcribe Video",
"type": "n8n-nodes-deapi.deapi",
"position": [
1344,
2096
],
"parameters": {
"source": "binary",
"options": {
"waitTimeout": 120
},
"resource": "video",
"operation": "transcribe",
"binaryPropertyName": "video"
},
"credentials": {
"deApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "a685c3d7-ba6e-4bf9-88c1-a2ffca1a628e",
"name": "Extract from File",
"type": "n8n-nodes-base.extractFromFile",
"position": [
1552,
2096
],
"parameters": {
"options": {},
"operation": "text",
"destinationKey": "text"
},
"typeVersion": 1.1
},
{
"id": "91159328-15ff-4f45-abf8-9189631d8bf4",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1840,
2096
],
"parameters": {
"text": "=Translate the following transcript into {{ $('Set Fields').item.json.target_language }}.\n\nReturn ONLY the translated text, without timestamps, line numbers, or formatting. Preserve the natural pacing and tone of the original speech.\n\nTranscript:\n{{ $json.text }}",
"options": {
"systemMessage": "You are a professional translator specializing in video localization. Your goal is to produce natural-sounding translations that work well when spoken aloud.\n\nKey principles:\n- Preserve the tone, energy, and intent of the original speech\n- Adapt idioms and cultural references for the target audience\n- Keep sentences at a similar length to the original for lip-sync compatibility\n- Use natural spoken language, not formal written style\n- Return ONLY the translated text \u2014 no explanations, notes, or formatting"
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "9bdee101-3077-46f9-8796-7baa8488bf8d",
"name": "Anthropic Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
1840,
2288
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "claude-opus-4-6",
"cachedResultName": "Claude Opus 4.6"
},
"options": {}
},
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "10f8b667-47bb-4333-a5d6-18b0617562f7",
"name": "deAPI Generate Speech",
"type": "n8n-nodes-deapi.deapi",
"position": [
2336,
2096
],
"parameters": {
"text": "={{ $json.output }}",
"model": "Qwen3_TTS_12Hz_1_7B_CustomVoice",
"options": {
"waitTimeout": 120
},
"resource": "audio",
"operation": "generateSpeech",
"qwen3Lang": "={{ $('Set Fields').item.json.target_language }}"
},
"credentials": {
"deApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "bdb0e104-d7a2-4d39-b30f-d7b000bda81c",
"name": "Merge Audio + Image",
"type": "n8n-nodes-base.merge",
"position": [
2672,
2272
],
"parameters": {
"mode": "combine",
"options": {},
"combineBy": "combineByPosition"
},
"typeVersion": 3.2
},
{
"id": "8d95a8c1-38ba-469b-94bb-41b4faedb3f4",
"name": "deAPI Generate From Audio",
"type": "n8n-nodes-deapi.deapi",
"position": [
2896,
2272
],
"parameters": {
"prompt": "A person speaking naturally to the camera, subtle head movements and facial expressions, professional lighting, medium close-up shot, steady camera",
"options": {
"frames": 241,
"firstFrame": "image",
"waitTimeout": 300
},
"resource": "video",
"operation": "generateFromAudio"
},
"credentials": {
"deApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"connections": {
"AI Agent": {
"main": [
[
{
"node": "deAPI Generate Speech",
"type": "main",
"index": 0
}
]
]
},
"Set Fields": {
"main": [
[
{
"node": "Read Source Video",
"type": "main",
"index": 0
},
{
"node": "Read Local Presenter Image",
"type": "main",
"index": 0
}
]
]
},
"Manual Trigger": {
"main": [
[
{
"node": "Set Fields",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Read Source Video": {
"main": [
[
{
"node": "deAPI Transcribe Video",
"type": "main",
"index": 0
}
]
]
},
"Merge Audio + Image": {
"main": [
[
{
"node": "deAPI Generate From Audio",
"type": "main",
"index": 0
}
]
]
},
"Anthropic Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"deAPI Generate Speech": {
"main": [
[
{
"node": "Merge Audio + Image",
"type": "main",
"index": 0
}
]
]
},
"deAPI Transcribe Video": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"deAPI Generate From Audio": {
"main": [
[]
]
},
"Read Local Presenter Image": {
"main": [
[
{
"node": "Merge Audio + Image",
"type": "main",
"index": 1
}
]
]
}
}
}
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.
anthropicApideApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Marketing teams localizing video content for international markets E-commerce brands creating product videos for multiple regions Agencies producing multilingual ad campaigns for global clients Educators and trainers adapting video courses for different language audiences Anyone…
Source: https://n8n.io/workflows/14662/ — 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.
Content creators who want a consistent on-screen avatar without filming themselves Marketing teams producing personalized video messages at scale Educators building video lessons with a virtual presen
Read Write File, N8N Nodes Deapi, Agent +1
Jd-Resume-Generator. Uses formTrigger, lmChatAnthropic, agent, readWriteFile. Event-driven trigger; 38 nodes.
Form Trigger, Anthropic Chat, Agent +2
E-commerce store owners using Shopify Product managers who need consistent product imagery Marketing teams looking to automate visual content creation Dropshipping businesses needing quick product pho
Shopify Trigger, Agent, Output Parser Structured +3
Marketing teams who need quick video ads without a production crew E-commerce sellers promoting products on social media Freelancers and agencies producing ad creatives for clients Anyone who wants to
Output Parser Structured, N8N Nodes Deapi, Anthropic Chat +3
Teams who upload meeting recordings to YouTube (unlisted or private) and want automated notes Project managers who need to track action items across recurring meetings Remote teams who want searchable
Rss Feed Read Trigger, N8N Nodes Deapi, Agent +4