Convert Japanese scripts to multilingual speech with GPT-4 and ElevenLabs

by Cheng Siong Chin ✓ · 82 views · created 2026-01-02 · Content Creation, Multimodal AI

What this workflow does

This AI workflow has 14 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenAI Chat Model.

How it runs

Trigger: Manually, when you click “Execute workflow”.

1. Workflow Configuration (Edit Fields (Set)): sets 7 fields: japaneseScript, targetLanguages, voiceId…
2. Translation Orchestrator Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (Translation Agent Tool); output parser: Structured Output Parser
3. Prepare Translation Request (Edit Fields (Set)): sets 6 fields: translatedText, language, voiceId…
4. ElevenLabs Text-to-Speech (HTTP Request): calls an HTTP API (POST)
5. Audio Quality Validation (Code): runs custom JavaScript code
6. Check Audio Quality (If): checks a condition and branches into true / false
7. Standardize Audio Output (Edit Fields (Set)): sets 6 fields: status, audioFileName, audioSizeKB…
8. Handle Quality Failure (Edit Fields (Set)): sets 4 fields: status, errorMessage, fileSize…

Services it uses

OpenAI Chat Model

Before you upgrade to n8n 3.0

Nodes used (9)

• Manual Triggern8n-nodes-base.manualTrigger
• Edit Fields (Set)n8n-nodes-base.set
• AI Agent@n8n/n8n-nodes-langchain.agent
• AI Agent Tool@n8n/n8n-nodes-langchain.agentTool
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• HTTP Requestn8n-nodes-base.httpRequest
• Coden8n-nodes-base.code
• Ifn8n-nodes-base.if

From the author

How It Works This workflow provides enterprise-grade translation and text-to-speech automation for international communication teams, content publishers, and localization services. It addresses producing high-quality multilingual audio content with consistent…

View the original on n8n.io → Check your own copy