luke/ai-podcast
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
142 Commits 3 Branches 0 Tags
main
Commit Graph

8 Commits

Author SHA1 Message Date
luke 0147be4e0c Normalization diagnostics + SFX track support 
- Detailed logging for normalize_track_items (item count, RMS, gain, applied/skipped)
- Add SFX track normalization (track 5)
- Will reveal why ad/ident normalization silently fails

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-21 02:14:34 -06:00
luke 762b5efc3b Strip silence: preserve music intro, fix ad normalization, smart loop range 
- Preserve first silence in first DIALOG region (music intro before host speaks)
- Fix ad/ident normalization using direct WAV reading (accessor failed after splits)
- Loop range starts 0.5s before audible music, ends at last item
- Disable broken music lead-in nudge (intro preservation handles it)
- Caller dialog model set to Grok for testing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-19 02:32:34 -06:00
luke 90e51698b8 Devon fixes, theme prompt rewrite, sentence trimmer, cost tracker, normalization 
- Fix Devon "if that makes sense" overuse (limit to once per show)
- Suppress Devon failed lookup notifications for self-initiated searches
- Strengthen show theme prompts (2/3 callers call because of theme)
- Fix sentence trimmer splitting on abbreviations (Mr. Mrs. Dr. etc.)
- Fix cost tracker data lost on server restart (persist in checkpoint)
- Ad/ident normalization targets -4dB below dialog for perceived loudness match
- Lower cross-speaker transition threshold to 5s

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-18 03:55:55 -06:00
luke 5d8ab57e20 Show theme feature, Irish music genre, strip silence overhaul 
- Add show theme UI in header bar + backend API (inject into caller prompts)
- Add Irish genre category for music dropdown
- Strip silence: RMS-based speaker detection (fixes Devon not being identified)
- Strip silence: Devon-specific 3s threshold for interjections
- Strip silence: sparse track item handling in shift logic
- Strip silence: music lead-in preservation after silence removal
- Strip silence: no max gap limit (IDENT/AD regions protect breaks)
- Add analyze_gaps.py tool for per-show threshold analysis

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-18 03:30:15 -06:00
luke 164cad456c Devon own stem/track/channel, per-category LLM routing, settings UI cleanup 
Audio:
- Devon gets own stem, Reaper track (Input 17), and configurable channel
- play_caller_audio accepts stem_name + channel_override params
- Reaper script checks 4 voice tracks (Host, Devon, Live Caller, AI Caller)
- postprod.py includes devon stem in gap detection

Cost optimization:
- Per-category model routing: Sonnet for caller dialog, Gemini Flash for everything else
- Estimated 65% cost reduction ($4.32 → ~$1.50/show)
- Category models configurable from settings UI

Frontend:
- Settings panel: clean routing grid for output channels, model routing grid for LLM categories
- Devon channel added to audio routing
- Share icon SVG fill fix (currentColor)
- Website homepage iterations

Publishing:
- Revert Castopod API workaround (API re-enabled)
- Fix container media path

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-16 17:05:19 -06:00
luke 0b091a1afd Homepage redesign, ep38 publish, Castopod fix, share icons, avatar gender 
Website:
- Full homepage redesign: new hero with punchy tagline, social proof strip
  with real caller quotes, featured episode spotlight, clips moved up
- Remove Q&A section, cover art from hero, secondary links
- Fix share icon fill (currentColor), add .sr-only class
- Bump cache versions to v=6

Backend:
- Blacklist Celeste voice
- Fix avatar gender caching with marker files
- Fix _match_voices_to_styles() bypassing BLACKLISTED_VOICES

Publishing:
- Fix Castopod container path (/var/www/castopod/ → /app/)
- Revert CLOUDFLARE_UPLOAD_LIMIT workaround (API fixed)
- Publish episode 38

Reaper:
- Dual silence threshold (2.5s transitions, 6s same-speaker)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-16 14:31:37 -06:00
luke d39cb3f3d4 Website overhaul: nav, accessibility, shared components, SEO, Reaper silence detection 
Website:
- Add persistent top nav across all pages
- Add skip-to-content links, focus-visible styles, ARIA on audio player
- Fix text contrast for WCAG AA compliance
- Add 600px breakpoint, mobile typography scaling
- Extract shared footer.js, player.js, episode.js components
- Episode pagination (10 + Load More), featured clip dedup
- Worker meta injection for social crawler OG tags
- Unify Plausible analytics proxy across all pages
- Sanitize innerHTML for XSS safety
- Custom 404 page, enhanced llms.txt, fix sitemap
- Bump cache versions to v=4

Reaper:
- Add dual silence threshold: 2.5s for speaker transitions, 6s for same-speaker gaps

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-16 00:56:29 -06:00
luke 3329cf9ac2 UI cleanup, Devon overhaul, bug fixes, publish ep36 
- Fix Devon double messages, add conversation persistence, voice-to-Devon when no caller
- Devon personality: weird/lovable intern on first day, handles name misspellings
- Fix caller gender/avatar mismatch (avatar seed includes gender)
- Reserve Sebastian voice for Silas, ban "eating at me" phrase harder
- Callers now hear Devon's commentary in conversation context
- CSS cleanup: expand compressed blocks, remove inline styles, fix Devon color to warm tawny
- Reaper silence threshold 7s → 6s
- Publish episode 36

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-14 16:42:21 -06:00