tcpsyn c7aac1b373 Make AI callers more dynamic with arcs, seeds, style gradients, and learning ...

- Conversation arc system: callers evolve through Opening → Building → Turn →
  Depth → Wind down stages, with style-based timing offsets
- Problem seeds: 80 short concept strings that the LLM expands into unique
  stories each time (50% of PROBLEMS picks use seeds vs full entries)
- Style gradients: 4 composable axes (energy, honesty, humor, confidence)
  with 625 combinations, used 50% of the time alongside handcrafted styles
- Call duration tracking: records metrics to data/call_metrics.json, learns
  which pools and style axes produce longer calls, nudges future picks ±15%

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-12 06:21:09 -06:00

backend

Make AI callers more dynamic with arcs, seeds, style gradients, and learning

2026-03-12 06:21:09 -06:00

data

Clips page, new episodes, TTS/audio improvements, publish pipeline updates

2026-03-12 05:38:58 -06:00

docs

Clips page, new episodes, TTS/audio improvements, publish pipeline updates

2026-03-12 05:38:58 -06:00

frontend

Upgrade Whisper to distil-large-v3, fix caller identity confusion, sort clips list

2026-03-05 12:46:51 -07:00

functions

Add banner, Apple Podcasts link, feed proxy, and fetch retry

2026-02-06 14:03:29 -07:00

tests

Update tests for SignalWire phone caller format

2026-02-05 17:47:50 -07:00

website

Clips page, new episodes, TTS/audio improvements, publish pipeline updates

2026-03-12 05:38:58 -06:00

.env.example

Move hardcoded secrets to .env, add .env.example

2026-03-05 15:19:20 -07:00

.github-last-push

Clips page, new episodes, TTS/audio improvements, publish pipeline updates

2026-03-12 05:38:58 -06:00

.gitignore

TTS fixes, Inworld improvements, footer redesign, episodes 15-25, invoice script fix

2026-03-02 12:38:58 -07:00

audio_settings.json

Clips page, new episodes, TTS/audio improvements, publish pipeline updates

2026-03-12 05:38:58 -06:00

CLAUDE.md

Clips page, new episodes, TTS/audio improvements, publish pipeline updates

2026-03-12 05:38:58 -06:00

deploy_stats_cron.sh

Move hardcoded secrets to .env, add .env.example

2026-03-05 15:19:20 -07:00

download_sounds.py

Initial commit: AI Radio Show web application

2026-02-04 23:11:20 -07:00

generate_callers.py

Initial commit: AI Radio Show web application

2026-02-04 23:11:20 -07:00

generate_sounds.py

Initial commit: AI Radio Show web application

2026-02-04 23:11:20 -07:00

make_clips.py

Clips page, new episodes, TTS/audio improvements, publish pipeline updates

2026-03-12 05:38:58 -06:00

make_social_post.py

TTS fixes, Inworld improvements, footer redesign, episodes 15-25, invoice script fix

2026-03-02 12:38:58 -07:00

podcast_stats.py

Move hardcoded secrets to .env, add .env.example

2026-03-05 15:19:20 -07:00

postprod.py

Add idents playback section — loads from idents/ folder, plays on ads channel

2026-02-23 22:24:40 -07:00

publish_episode.py

Clips page, new episodes, TTS/audio improvements, publish pipeline updates

2026-03-12 05:38:58 -06:00

radio_show.py

Initial commit: AI Radio Show web application

2026-02-04 23:11:20 -07:00

radio_simple.py

Initial commit: AI Radio Show web application

2026-02-04 23:11:20 -07:00

relabel_transcripts.py

Add speaker-labeled transcripts, favicon, host stream fix, episode page

2026-02-11 15:19:45 -07:00

requirements-web.txt

Initial commit: AI Radio Show web application

2026-02-04 23:11:20 -07:00

run.sh

Fix LLM model list, Castopod API, and server runner

2026-02-06 01:56:09 -07:00

test.html

Initial commit: AI Radio Show web application

2026-02-04 23:11:20 -07:00

upload_clips.py

Clips page, new episodes, TTS/audio improvements, publish pipeline updates

2026-03-12 05:38:58 -06:00

yt_auth.py

Add direct YouTube upload to publish pipeline, publish ep14

2026-02-17 15:07:16 -07:00

Description

AI Radio Show - web-based podcast production with multiple TTS providers

11 MiB

Languages

Python 76.7%

HTML 12.5%

JavaScript 5.2%

CSS 3.4%

Lua 1.9%

Other 0.3%