Play 94
AI Podcast Generator
High✅ Ready
Text-to-podcast pipeline with multi-speaker voice synthesis and music transitions.
Text-to-podcast pipeline with multi-speaker voice synthesis, music transitions, chapter markers, and content safety review. Converts blog posts, research papers, or meeting notes into professionally narrated audio content using Azure AI Voice Live SDK.
Architecture Pattern
Podcast pipeline: content ingestion - script generation - multi-voice synthesis - music layering - chapter marking - safety review
Azure Services
Azure AI SpeechAzure OpenAIAzure Blob StorageAzure CDNAzure Functions
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Podcast Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (217 lines), evaluate (105 lines), tune (228 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + Speech inputs + envFile
TuneKit (AI Config)
- config/openai.json - script generation and content adaptation prompts
- config/podcast.json - voice personas, speaking rates, music styles
- config/guardrails.json - content safety thresholds, audio quality minimums
- evaluation/eval.py - Audio quality >4.0 MOS, Content fidelity >90%
Tuning Parameters
Voice persona selectionSpeaking rateMusic transition styleChapter detection sensitivityContent safety threshold
Estimated Cost
Dev/Test
$80-200/mo
Production
$2K-8K/mo