How rama-l7/telugu_podcast_agent works
Telugu Podcast Agent processes YouTube links from a Google Sheet: it validates and saves transcripts, then can generate a Telugu two-speaker script, synthesize audio, upload it to Drive, and update the sheet. The README identifies transcript processing as the completed default workflow and later stages as roadmap; the source index and excerpts also show full-pipeline and watcher components. Some implementation details are unsampled, so the graph omits uncertain relationships.
Main entry points: sheet_monitor.py Sheet pipeline · transcript.py Transcript extraction · drive_uploader.py Drive uploader · retry_utils.py Retry and backoff
Components 17
Workflow orchestration
- CLI orchestrator
main.py - Polling watcher
src/watcher.py - Sheet pipeline
src/sheet_monitor.py
Content processing
- Transcript extraction
src/transcript.py - Telugu script generation
src/script_generator.py - LLM adapter
src/llm.py - Speech synthesis
src/tts.py
External integrations
- Google Sheet
- Local transcripts
output/transcripts - YouTube captions
- LLM providers
- Local audio output
output - Drive uploader
src/drive_uploader.py - Google Drive
Shared runtime support
- Retry and backoff
src/retry_utils.py - Runtime configuration
config.py
Other components
- Sheet operator
Connections 18
- Sheet operator → Google Sheet: enters links
README.md - CLI orchestrator → Sheet pipeline: runs pipeline
main.py - CLI orchestrator → Polling watcher: starts watch
main.py - Polling watcher → Sheet pipeline: runs pipeline
src/watcher.py - Sheet pipeline → Google Sheet: reads and updates
README.md - Sheet pipeline → Transcript extraction: fetches and saves
src/sheet_monitor.py - Transcript extraction → YouTube captions: fetches captions
README.md - Transcript extraction → Local transcripts: writes transcripts
README.md - Sheet pipeline → Telugu script generation: generates script
src/sheet_monitor.py - Telugu script generation → LLM adapter: requests generation
src/script_generator.py - LLM adapter → LLM providers: calls provider
src/llm.py - Sheet pipeline → Speech synthesis: synthesizes speech
src/sheet_monitor.py - Speech synthesis → Local audio output: writes audio
README.md - Sheet pipeline → Drive uploader: uploads audio
README.md - Drive uploader → Google Drive: uploads file
src/drive_uploader.py - Transcript extraction → Retry and backoff: uses retries
src/transcript.py - Drive uploader → Retry and backoff: uses retries
src/drive_uploader.py - Retry and backoff → Runtime configuration: reads retry settings
src/retry_utils.py