test-repo/docs/PODCAST_PRD.md

Daily Digest Podcast - PRD & Roadmap

Current State

✅ DONE - What's Built & Working

• TTS generation (macOS say - built-in, no external API)
• Audio mixing with ffmpeg (Intro → Speech → Outro)
• Music files in blog-creator/public/podcast-audio/
• Environment config set up
• Daily digest workflow at 7am CST
• TESTED: Audio generated successfully with music!

---

What's Left to Do

1. Integrate TTS into Daily Digest Cron

• The 7am cron creates digest but doesn't auto-generate audio
• Need to add TTS call to the daily-digest workflow

2. Refine Audio Mixing (Optional)

• Current: Simple concat with volume adjustment
• Could add crossfades for smoother transitions
• Could add background music bed under speech

---

Configuration (Already Set)

# blog-backup .env.local
ENABLE_TTS=true
TTS_PROVIDER=macsay
ENABLE_PODCAST_MUSIC=true
INTRO_MUSIC_URL=/Users/mattbruce/Documents/Projects/OpenClaw/Web/blog-creator/public/podcast-audio/intro.mp3
OUTRO_MUSIC_URL=/Users/mattbruce/Documents/Projects/OpenClaw/Web/blog-creator/public/podcast-audio/outro.mp3

---

File Locations

Component	Location
PRD	~/.openclaw/workspace/docs/PODCAST_PRD.md
Skills	blog-creator/skills/daily-digest/
Intro Music	blog-creator/public/podcast-audio/intro.mp3
Outro Music	blog-creator/public/podcast-audio/outro.mp3
TTS + Mixing Code	blog-backup/src/lib/tts.ts
Daily Digest API	blog-backup/src/app/api/digest/route.ts

---

Test Result

Test successful! Generated audio file:

• URL: https://qnatchrjlpehiijwtreh.supabase.co/storage/v1/object/public/podcast-audio/tts-1772476798520.mp3
• Duration: 108 seconds
• Contains: Intro music + TTS speech + Outro music