lukeandClaude Opus 4.6 54ad04ae09 LLM: per-model params for caller_dialog + longer timeouts ...

Different models need different tuning for natural conversation:
Qwen gets high frequency penalty to fight repetition loops, Llama
gets warmer temp to reduce terseness, Grok/Mistral/DeepSeek/Kimi get
slightly warmer than Sonnet defaults. Bumps base httpx timeout from
10s to 30s and fallback per-call timeout from 8s to 20s.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-09 23:39:45 -06:00

backend

LLM: per-model params for caller_dialog + longer timeouts

2026-04-09 23:39:45 -06:00

data

Add MIT license, add X to social posting platforms

2026-03-17 01:39:25 -06:00

docs

Add caller generation redesign plan

2026-04-05 01:57:32 -06:00

frontend

Cost dashboard: TTS providers endpoint, header link, polish

2026-04-09 23:39:40 -06:00

functions

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

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

reaper

Normalization diagnostics + SFX track support

2026-03-21 02:14:34 -06:00

tests

Update tests for SignalWire phone caller format

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

website

Homepage redesign, ep38 publish, Castopod fix, share icons, avatar gender

2026-03-16 14:31:37 -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

Ignore .worktrees/ directory

2026-04-05 01:58:32 -06:00

analyze_gaps.py

Show theme feature, Irish music genre, strip silence overhaul

2026-03-18 03:30:15 -06:00

audio_settings.json

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

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

backup.sh

Full app audit: 24 fixes across backend, frontend, infra, content, social

2026-03-18 14:57:50 -06:00

CLAUDE.md

Caller generation overhaul, Devon intern, frontend redesign

2026-03-14 01:54:08 -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

fetch_music.py

Devon personality + Whisper name fix + music vocal filtering

2026-03-22 23:59:03 -06:00

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

LICENSE

Add MIT license, add X to social posting platforms

2026-03-17 01:39:25 -06:00

make_clips.py

Make make_clips.py resilient — timeouts, retries, skip-on-failure

2026-03-20 17:36:41 -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

Expand all caller topic pools, add cross-episode topic dedup, publish ep35

2026-03-13 05:45:22 -06:00

postprod.py

Devon own stem/track/channel, per-category LLM routing, settings UI cleanup

2026-03-16 17:05:19 -06:00

publish_episode.py

Full app audit: 24 fixes across backend, frontend, infra, content, social

2026-03-18 14:57:50 -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

scan_music_vocals.py

Devon personality + Whisper name fix + music vocal filtering

2026-03-22 23:59:03 -06:00

test.html

Initial commit: AI Radio Show web application

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

upload_clips.py

Fix LinkedIn posting to use correct account, blocklist personal profile

2026-03-18 14:02:47 -06:00

yt_auth.py

Add direct YouTube upload to publish pipeline, publish ep14

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

S

Description

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

MIT

9.6 MiB

Languages

HTML 78.2%

Python 17.3%

JavaScript 2%

CSS 1.3%

Lua 1%

Other 0.2%