← Commit history

Publish 1.9.48

John Lauer ·fa8a8324b3 ·1mo ago ·parent 7a31e69
4 files changed +29−2
bin/adom-tts
⋯ 1 unchanged line ⋯
package.json+1−1
@@ -1,6 +1,6 @@ {   "slug": "adom-tts",-  "version": "1.9.47",+  "version": "1.9.48",   "type": "app",   "description": "Adom's shared text-to-speech CLI + Playground. Reads your AI answers back to you while driving, and renders perfectly-timed voiceover tracks for demo videos.",   "license": "MIT",
page.json+22−1
@@ -4,7 +4,7 @@   "slug": "adom-tts",   "title": "Adom TTS: Text to Speech",   "brief": "Adom's shared voice service. Reads your AI's answers back to you while you drive, and renders perfectly-timed voiceover tracks for your demo videos, so you never record your own voice.",-  "version": "1.9.47",+  "version": "1.9.48",   "license": "MIT",   "tags": [     "tts",@@ -12,6 +12,7 @@     "audio",     "demo",     "accessibility",+    "cli",     "open-source",     "mit"   ],@@ -64,5 +65,25 @@   ],   "install": {     "binary_name": "adom-tts"+  },+  "description": "Adom's shared text-to-speech CLI + Playground. Reads your AI answers back to you while driving, and renders perfectly-timed voiceover tracks for demo videos.",+  "dependencies": {},+  "scripts": {+    "install": "./install.sh",+    "uninstall": "./uninstall.sh"+  },+  "needs_sudo": false,+  "files": [+    "package.json",+    "install.sh",+    "uninstall.sh",+    "bin/adom-tts",+    "skills/**",+    "completions/**"+  ],+  "org": "adom",+  "author": {+    "name": "John Lauer",+    "email": "[email protected]"   } }\ No newline at end of file
skills/adom-tts/SKILL.md+6
@@ -70,6 +70,12 @@ line); it is an internal host, not something a caller ever opens by hand.    holds every thread's clips, and waiting will never clear it. A thread once    sat through a 226-second `--confirm` timeout believing only the human could    press play, so the failure output now names this command for you.+   Stale clips piling up behind a pause? Retract WAITING clips (never the+   playing one) with `adom-tts queue clear --mine <thread>` (yours only) or+   `--all`; drop one with `adom-tts queue drop <clip|req-id>`; end the clip+   that is playing right now with `adom-tts control skip`. Dropped and skipped+   clips land in History, never silently destroyed. The ACCEPTED line also+   tells you roughly how many seconds of audio are queued ahead of yours. 5. No separate "here's a summary" text response on top (the user can't see it anyway).  This is the canonical drive-mode pattern. Memorize it. The user's literal words won't always say "TTS" — they'll say "I'm driving, just read me your answer." That IS the trigger.