Skip to main content

Translate English scripts to multilingual audio with GPT-4 and ElevenLabs

Workflow preview

Translate English scripts to multilingual audio with GPT-4 and ElevenLabs preview
Open on n8n.io

Important notice

This workflow is provided as-is. Please review and test before using in production.

Overview

πŸ“Š Description

Automate multilingual voice content creation by translating an English script into multiple languages and generating natural-sounding audio files using AI. πŸŒπŸŽ™οΈ This workflow receives a script via webhook, translates it into selected target languages using GPT-4, converts each translation into high-quality speech with ElevenLabs, and uploads the resulting MP3 files to Google Drive. It’s ideal for teams producing localized videos, podcasts, courses, or educational content at scale β€” without manual translation or recording. πŸš€βœ¨

πŸ” What This Template Does

1️⃣ Receives an English script and target languages via webhook. 🌐 2️⃣ Extracts and normalizes request parameters for processing. πŸ“ 3️⃣ Uses GPT-4 with a strict JSON schema to translate the script into multiple languages. πŸ€–πŸŒ 4️⃣ Splits each translated language into individual processing items. πŸ”€ 5️⃣ Converts each translation into natural-sounding speech using ElevenLabs. πŸŽ™οΈ 6️⃣ Processes translations sequentially to avoid API limits. ⏳ 7️⃣ Uploads language-specific MP3 files to Google Drive with clean naming. ☁️ 8️⃣ Returns generated audio as a webhook response for frontend usage. πŸ” 9️⃣ Triggers Slack alerts if any workflow error occurs. 🚨

⭐ Key Benefits

βœ… Instantly localizes audio content into multiple languages βœ… Produces human-quality voiceovers without recording studios βœ… Ensures consistent tone and meaning across all translations βœ… Fully automated from script input to audio delivery βœ… Scales easily for videos, podcasts, training, and education βœ… Clean Google Drive storage for easy access and reuse

🧩 Features

  • Webhook-based script ingestion
  • GPT-4 multilingual translation with structured JSON output
  • AI memory for consistent translation behavior
  • ElevenLabs multilingual text-to-speech generation
  • Batch processing for multiple languages
  • Google Drive MP3 upload with language-based filenames
  • Webhook audio response for frontend apps
  • Slack-based error handling and alerts

πŸ” Requirements

  • OpenAI API key (GPT-4 / GPT-4.1-mini)
  • ElevenLabs API key (multilingual voice model)
  • Google Drive OAuth2 credentials
  • Slack API credentials (for error alerts)
  • Webhook client sending Script, first_language, and second_language

🎯 Target Audience

  • Content teams creating localized videos or podcasts
  • EdTech platforms producing multilingual learning material
  • Marketing teams localizing campaigns across regions
  • Creators building AI-driven voice pipelines
  • Automation teams integrating audio localization into products