How binbinao/mypodcast works
myPodcast turns Markdown articles into reviewed podcast scripts, then synthesizes audio and publishes RSS and a program site. The primary workflow is raw article → episode planning and script preparation → human review → read-only build → TTS audio and publication artifacts. README documents the major stages, selectable speech backends, voice selection, prosody, validation, naming rules, and resumable builds. Connections for unsampled modules are limited to documented relationships; local Qwen service internals are represented only at the documented boundary.
Main entry points: prepare.py Prepare workflow · build.py Build orchestrator · tts.py TTS backend router · base.py Backend registry
Components 24
Content and review
- Source articles
raw - Reviewed scripts
drafts
Script preparation
- Prepare workflow
src/prepare.py - Article ingestion
src/ingest.py - Episode planning
src/split.py - Format and voice decisions
src/decisions.py - Script generation
src/generate.py - LLM service client
src/llm.py - Draft lifecycle
src/stages.py - Path and slug rules
src/naming.py
Audio generation
- Build orchestrator
src/build.py - Script validation
src/validate.py - Voice selection
src/voicecaster.py - Prosody planning
src/prosody.py - TTS backend router
src/tts.py - Backend registry
src/backends/base.py - Local Qwen backend
src/backends/qwen3_local.py - Cloud TTS backends
src/backends - Local Qwen service
scripts/qwen3-tts-local
Publishing
- Audio and manifests
output - RSS and site generator
src/feed.py
Other components
- Article author
- Script reviewer
- Podcast listeners
Connections 26
- Article author → Source articles: writes
README.md - Source articles → Prepare workflow: prepares
README.md - Prepare workflow → Article ingestion: ingests
README.md - Prepare workflow → Episode planning: plans episodes
README.md - Prepare workflow → Format and voice decisions: collects decisions
README.md - Prepare workflow → Script generation: generates scripts
README.md - Script generation → LLM service client: requests completion
README.md - Prepare workflow → Reviewed scripts: writes drafts
README.md - Script reviewer → Reviewed scripts: edits scripts
README.md - Prepare workflow → Draft lifecycle: sets review stage
README.md - Prepare workflow → Path and slug rules: enforces paths
README.md - Reviewed scripts → Build orchestrator: builds from
README.md - Build orchestrator → Draft lifecycle: checks stage
README.md - Build orchestrator → Script validation: validates scripts
README.md - Build orchestrator → Voice selection: selects voice
README.md - Voice selection → LLM service client: infers voice
README.md - Build orchestrator → TTS backend router: synthesizes audio
README.md - TTS backend router → Prosody planning: plans prosody
README.md - TTS backend router → Backend registry: routes backend
README.md - Backend registry → Local Qwen backend: registers
README.md - Backend registry → Cloud TTS backends: registers
README.md - Local Qwen backend → Local Qwen service: requests speech
README.md - Build orchestrator → Audio and manifests: writes artifacts
README.md - Build orchestrator → RSS and site generator: refreshes publication
README.md - RSS and site generator → Audio and manifests: writes RSS and site
README.md - Audio and manifests → Podcast listeners: serves episodes
README.md