Automated News to Podcast Script Generation (EN/ZH)
detail.loadingPreview
Generates podcast scripts from BBC news articles, with potential for multilingual output and TTS integration.
About This Workflow
This workflow automates the process of converting news articles into engaging podcast scripts. It starts by fetching news from BBC, extracting relevant article details, classifying their suitability for podcasting using an LLM, and then generating a podcast script. The script can then be fed into a text-to-speech engine for audio generation. The workflow also includes a crucial step to conditionally handle the output based on whether a "podcast_script" is generated, and it prepares for potential multilingual content by design, although the current implementation focuses on English script generation.
Key Features
- Web Scraping: Fetches news articles from BBC.com.
- HTML Extraction: Extracts titles, links, and descriptions from news articles.
- LLM-based Classification: Uses Gemini (via
textClassifier) to assess the suitability of news for a podcast narrative. - Detail Fetching: Retrieves full article content for suitable news items.
- LLM-powered Script Generation: Employs Gemini (via
chainLlm) to transform news content into a conversational podcast script. - Conditional Logic: Handles scenarios where a podcast script might not be generated.
- Text-to-Speech Integration: Prepares for Hugging Face TTS for audio output.
- Structured Output: Aims for JSON output for the podcast script.
- Scalability: Designed to process multiple news items and aggregate data.
How To Use
- Trigger: Start the workflow by clicking 'Test workflow'.
- Fetch BBC News: The
Fetch BBC News Pagenode retrieves the main BBC news page. - Extract News Blocks:
Extract News Blockuses CSS selectors to identify news titles and links. - Split Titles:
Split Outseparates the extractednewsTitlefor further processing. - Extract News Content:
Extract News Contentfurther extracts the title, link, and description for each news item. - Limit Items:
Limit 10 Itemsrestricts the processing to the top 10 news items. - Classify News:
News Classifier(using Gemini) evaluates if each news item's title and description are suitable for a podcast. - Fetch Details: For suitable items,
Fetch BBC News Detailretrieves the full article content from its URL. - Extract Details:
Extract Detailparses the HTML of the detailed article page to get the main content (newsDetail). - Filter Empty Details:
Filter Empty Detailremoves items where no news detail was found. - Aggregate Data:
Aggregatecombines all processed news details into a single data item. - Generate Podcast Script:
Basic Podcast LLM Chain(using Gemini) converts the aggregated news details into a conversational podcast script, following the detailed prompt. - Output Parser:
Output Parserhelps structure the LLM's output. - Conditional Handling:
If script existschecks if apodcast_scriptwas generated. - Text-to-Speech: If a script exists,
Hugging Face Text-to-Speech.is called to convert the script into audio. Note: The current JSON output doesn't explicitly show the Chinese translation generation, but the prompt forBasic Podcast LLM Chainis designed to create an English script for a podcast. To generate Chinese metadata, additional steps involving translation nodes (e.g., Google Translate) would be required after the content extraction and classification steps.
Apps Used
Workflow JSON
{
"id": "617628cd-e0fa-4b79-81a8-8ea851826591",
"name": "Automated News to Podcast Script Generation (EN/ZH)",
"nodes": 26,
"category": "Content Generation",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 617628cd-e0fa...
About the Author
Free n8n Workflows Official
System Admin
The official repository for verified enterprise-grade workflows.
Statistics
Related Workflows
Discover more workflows you might like
Structured Metadata Generation for English and Chinese
This workflow automates the generation of structured metadata in both English and Chinese, leveraging Slack interactions and external API calls.
Perplexity Research to HTML Web Page Generator
This workflow takes a research topic, generates structured content using AI, and converts it into a responsive HTML web page styled with Tailwind CSS.
Wikipedia Podcast Telegram Bot
Generates podcast episodes about Wikipedia articles via Telegram.