AI Workflow

AI Audio Summary Generator

Personal Project

A multi-stage AI workflow that transforms topics into audio briefs through research, summarization, evaluation, and narration. An LLM-as-judge quality gate catches weak outputs before they consume TTS resources or reach users.

n8n workflow OpenAI Agent Perplexity n8n Eval OpenAI TTS

How It Works

1
User submits topic query
2
AI Agent invokes Perplexity tool to retrieve current, cited information
3
Agent synthesizes research into audio-optimized script
4
LLM-as-judge evaluates helpfulness before proceeding
5
TTS converts approved scripts to natural speech
6
User receives quality-gated audio brief
AI Audio Summary Generator workflow diagram showing the n8n workflow with topic input, Perplexity research, AI summarization, evaluation, and OpenAI TTS output

Product Decisions

Stage Technology Product Rationale
Agent OpenAI + Simple Memory Agentic architecture enables dynamic tool use; memory supports follow-up queries
Research Tool Perplexity Grounded retrieval with citations prevents hallucinated facts in audio
Evaluation n8n Eval (Helpfulness) Quality gate prevents low-value outputs from consuming TTS credits
Narration OpenAI TTS Natural voice quality critical for audio content users will actually finish
Audio Length 2-3 minute cap Allows more users and testers to try the feature without hitting API limits

Why evaluate before TTS: Audio generation is the most expensive step. An LLM-as-judge quality gate ensures only helpful summaries proceed, optimizing both cost and user experience.

What I Learned

  • 💡 To ensure content is helpful, I used n8n's evaluation node which uses an LLM-as-judge to score the output. Based on the score, the workflow decides whether to regenerate or return the result.
  • 💡 AI-generated content without real data sounds generic. Grounding the output in researched facts made the difference between content users skip and content they finish.