Adom TTS: Text to Speech

@@ -0,0 +1,127 @@+#!/usr/bin/env python3+"""Stage the 4 demo scenes as self-contained HTML (states of the real player UI)."""+import os, json, pathlib++ROOT = pathlib.Path(__file__).resolve().parent.parent+OUT = pathlib.Path('/tmp/ttsdemo/scenes'); OUT.mkdir(parents=True, exist_ok=True)+player = (ROOT / 'src/player.html').read_text().replace('{{VERSION}}', '1.9.20')++CAPTION_CSS = """+<style>.demo-cap{position:fixed;top:52px;left:50%;transform:translateX(-50%);z-index:99;+background:rgba(13,17,23,.92);border:1px solid #2b3a52;border-radius:999px;padding:6px 18px;+font:600 13.5px 'Familjen Grotesk',system-ui,sans-serif;color:#7fe3dd;box-shadow:0 6px 24px rgba(0,0,0,.5)}</style>+"""++def cap(text):+    return CAPTION_CSS + f'<div class="demo-cap">{text}</div>'++WORDS1 = ("This is the flight-search thread. Round trip to Denver looks best on Tuesday: "+          "two forty five nonstop, four hundred twelve dollars on United. Want me to hold it?")++# ---- scene 1: player mid-karaoke ----+inj1 = cap("One shared player for all your AI threads") + """+<script>window.addEventListener('load',function(){+var words=%s.split(" ");+try{applyClip({id:1,title:'flight-answer.mp3',meta:'en-US-AndrewNeural',label:'flight-search',+  desc:'Denver flight options — best is Tue 2:45pm nonstop $412',words:words});}catch(e){}+var a=document.getElementById('a'); a.dispatchEvent(new Event('playing'));+var old=document.getElementById('live'); if(old){var neo=old.cloneNode(false);neo.className='led ok';neo.id='live2';old.parentNode.replaceChild(neo,old);}+var di=document.getElementById('diag'); if(di)di.remove();+var spans=document.querySelectorAll('.transcript w'); var i=0; var total=16.0; var t=0;+setInterval(function(){+  var s=document.getElementById('status'); if(s){s.textContent='playing';s.className='pill playing';}+  document.body.classList.add('is-playing');+  var pi=document.querySelector('#playicon path'); if(pi)pi.setAttribute('d','M6 5h4v14H6zM14 5h4v14h-4z');+},80);+setInterval(function(){+  if(i<spans.length){ spans.forEach(function(el,k){el.classList.toggle('active',k===i);el.classList.toggle('spoken',k<i);}); i++; }+  t=Math.min(total,t+0.42);+  var c=document.getElementById('cur'); if(c)c.textContent='0:'+String(Math.floor(t)).padStart(2,'0');+  var d=document.getElementById('dur'); if(d)d.textContent='0:16';+  var sk=document.getElementById('seek'); if(sk)sk.value=Math.round(t/total*1000);+},420);+});</script>""" % json.dumps(WORDS1)+(OUT / 'player.html').write_text(player.replace('</body>', inj1 + '</body>'))++# ---- scene 3: history + replay preempt ----+inj3 = cap("Missed a clip? It waits for you in History") + """+<script>window.addEventListener('load',function(){+var words="Missed clips wait for you right here in the history, one tap from playing again.".split(" ");+try{applyClip({id:1,title:'reply.mp3',meta:'en-US-AndrewNeural',label:'Adom-TTS',desc:'how the replayable history works',words:words});}catch(e){}+var now=Date.now();+renderHistory([+ {seq:1,ts_ms:now-35000,label:'Adom-TTS',desc:'how the replayable history works',verdict:'ok',dur_s:11.2},+ {seq:2,ts_ms:now-160000,label:'flight-search',desc:'Denver flight options — best is Tue 2:45pm nonstop $412',verdict:'ok',dur_s:16.4},+ {seq:3,ts_ms:now-380000,label:'deploy-watch',desc:'nightly deploy finished, zero errors',verdict:'no-playback',dur_s:24.0},+ {seq:4,ts_ms:now-1500000,label:'login-bug',desc:'login fix verified on prod',verdict:'ok',dur_s:19.8}+], now);+var a=document.getElementById('a'); a.dispatchEvent(new Event('playing'));+var old=document.getElementById('live'); if(old){var neo=old.cloneNode(false);neo.className='led ok';neo.id='live2';old.parentNode.replaceChild(neo,old);}+var di=document.getElementById('diag'); if(di)di.remove();+setInterval(function(){var s=document.getElementById('status'); if(s){s.textContent='playing';s.className='pill playing';} document.body.classList.add('is-playing');+  var pi=document.querySelector('#playicon path'); if(pi)pi.setAttribute('d','M6 5h4v14H6zM14 5h4v14h-4z');},80);+// beat: 3s in, pulse the missed row; 6s in, flash its replay button; 8s, swap to replay+setTimeout(function(){var rows=document.querySelectorAll('.hist-row'); if(rows[2]){rows[2].style.transition='background .4s';rows[2].style.background='rgba(212,160,23,.12)';}},3000);+setTimeout(function(){var b=document.querySelectorAll('.hist-replay')[2]; if(b){b.style.transition='transform .25s, background .25s';b.style.background='rgba(0,184,177,.35)';b.style.transform='scale(1.35)';setTimeout(function(){b.style.transform='scale(1)';b.textContent='✓';},450);}},6000);+setTimeout(function(){+  var w2="nightly deploy finished, zero errors, all services healthy after the rollout.".split(" ");+  try{applyClip({id:2,title:'deploy-note.mp3',meta:'en-US-AndrewNeural',label:'deploy-watch',desc:'(replay) nightly deploy finished, zero errors',words:w2});}catch(e){}+  var a2=document.getElementById('a'); a2.dispatchEvent(new Event('playing'));+  var spans=document.querySelectorAll('.transcript w'); var i=0;+  setInterval(function(){ if(i<spans.length){spans.forEach(function(el,k){el.classList.toggle('active',k===i);el.classList.toggle('spoken',k<i);}); i++;} },430);+},8200);+});</script>"""+(OUT / 'history.html').write_text(player.replace('</body>', inj3 + '</body>'))++# ---- scene 2: verified send (terminal typing) ----+term = """<!doctype html><html><head><style>+body{margin:0;background:#0d1117;display:flex;align-items:center;justify-content:center;min-height:100vh;font-family:ui-monospace,Menlo,monospace}+.term{width:820px;background:#0a0e14;border:1px solid #2b3a52;border-radius:12px;box-shadow:0 18px 50px rgba(0,0,0,.55);overflow:hidden}+.bar{height:34px;background:#161b22;border-bottom:1px solid #2b3a52;display:flex;align-items:center;padding:0 12px;color:#8b98a5;font-size:12px}+.bar .dot{width:10px;height:10px;border-radius:50%;background:#2b3a52;margin-right:6px}+pre{margin:0;padding:18px 20px;font-size:14px;line-height:1.7;color:#e6edf3;white-space:pre-wrap;min-height:330px}+.p{color:#7fe3dd}.c{color:#8b98a5}.g{color:#3fb950}+.cursor{display:inline-block;width:8px;height:16px;background:#7fe3dd;vertical-align:-2px;animation:bl 1s steps(1) infinite}+@keyframes bl{50%{opacity:0}}+CAPCSS</style></head><body>+CAPDIV+<div class="term"><div class="bar"><span class="dot"></span><span class="dot"></span><span class="dot"></span>claude — adom-tts</div><pre id="t"><span class="p">$</span> <span id="cmd"></span><span class="cursor" id="cur"></span><span id="out"></span></pre></div>+<script>+var CMD = 'adom-tts say "This is the flight-search thread — best Denver option is Tuesday 2:45pm nonstop." \\\\\\n    --thread "flight-search" --desc "Denver flight options" \\\\\\n    --out /tmp/answer.mp3 --play --confirm';+var i=0;+var typer=setInterval(function(){+  if(i<CMD.length){ document.getElementById('cmd').textContent=CMD.slice(0,++i); }+  else clearInterval(typer);+},34);+var OUT=[+ [5200,'\\n\\n→ /tmp/answer.mp3 (98304 bytes, cache=miss, hash=a1b2c3d4e5f6)'],+ [6100,'\\n<span class="c"># ACCEPTED "answer.mp3" — next up in the shared player.</span>'],+ [7000,'\\n<span class="c"># to KNOW it played: adom-tts check answer.mp3 — or --confirm blocks until heard.</span>'],+ [10300,'\\n\\n<span class="g">✓ CONFIRMED: "answer.mp3" played fully to the human (16/16s)</span>']+];+OUT.forEach(function(o){ setTimeout(function(){ document.getElementById('out').innerHTML+=o[1]; document.getElementById('cur').style.display='none'; }, o[0]); });+</script></body></html>"""+term = term.replace('CAPCSS', CAPTION_CSS.replace('<style>','').replace('</style>',''))+term = term.replace('CAPDIV', '<div class="demo-cap">Playback is verified, never assumed</div>')+(OUT / 'verify.html').write_text(term)++# ---- scene 4: outro (hero slow zoom + install typing) ----+hero_path = ROOT / 'screenshots/hero-v3.png'+outro = """<!doctype html><html><head><style>+body{margin:0;background:#0d1117;min-height:100vh;display:flex;flex-direction:column;align-items:center;justify-content:center;overflow:hidden;font-family:ui-monospace,Menlo,monospace}+.wrap{width:860px;border-radius:14px;overflow:hidden;border:1px solid #2b3a52;box-shadow:0 18px 60px rgba(0,0,0,.6)}+img{width:100%%;display:block;animation:zoom 14s linear forwards}+@keyframes zoom{from{transform:scale(1)}to{transform:scale(1.07)}}+.inst{margin-top:26px;font-size:16px;color:#7fe3dd;background:#0a0e14;border:1px solid #2b3a52;border-radius:10px;padding:12px 22px}+.cursor{display:inline-block;width:8px;height:16px;background:#7fe3dd;vertical-align:-2px;animation:bl 1s steps(1) infinite}+@keyframes bl{50%%{opacity:0}}+</style></head><body>+<div class="wrap"><img src="file://%s"></div>+<div class="inst"><span id="cmd"></span><span class="cursor"></span></div>+<script>+var CMD='adom-wiki pkg install adom/adom-tts'; var i=0;+setTimeout(function(){ var t=setInterval(function(){ if(i<CMD.length){document.getElementById('cmd').textContent=CMD.slice(0,++i);} else clearInterval(t); },50); },1500);+</script></body></html>""" % str(hero_path)+(OUT / 'outro.html').write_text(outro)++print("scenes:", sorted(p.name for p in OUT.iterdir()))

@@ -0,0 +1,120 @@+---+name: tts-pronunciation+description: Canonical table of TTS pronunciation overrides for Adom tool names, acronyms, and product terms that neural TTS engines (edge-tts, piper, azure, eleven-labs) mispronounce. Use when writing narration for any demo / walkthrough / tour / voiceover — look up each Adom-ish term in the table and spell it phonetically in the narration column. Use BEFORE rendering any TTS audio, not after.+  Trigger words: tts pronunciation, tts pronounce, mispronounce, how do I make TTS say, edge-tts pronounce, narration pronunciation, speak adom-tsci, demo narration phonetics.+  Also fires automatically whenever another skill (demo-recording, video-post, voiceover-over-a-recording) is drafting narration text.+---++# TTS pronunciation — canonical table++Single source of truth for how to write Adom tool names, acronyms, and product terms in narration so neural TTS engines voice them correctly. Every demo-recording / video-post / voiceover flow should consult this file at script-write time (not at render time — fixing mistakes after mux means re-rendering N clips).++## 🛑 The one rule++**If the TTS engine would read a word as something other than what a listener expects, rewrite it in the narration.** The most common fix is spelling an acronym out as individual letters separated by spaces — `adom-tsci` → `adom t s c i`. Edge-TTS and Piper both read letter-space-letter as individual letter names. No-space gets parsed as a single word and butchered.++Captions and on-screen text always use the real name (`adom-tsci`). Only the narration column gets phoneticized.++## The table++Source-of-truth data file: [`pronunciations.json`](pronunciations.json) (same dir). This table is rendered from that file; update the JSON and this section regenerates on skill install.++| Written in product / caption | Narration spelling (what the TTS sees) | Engines confirmed | Reason |+|---|---|---|---|+| `adom-tsci` | `adom t s c i` | edge-tts, piper | TTS reads `tsci` as "sci" / "ski"; letter-by-letter is the intended reading |+| `tscircuit` | `t s circuit` | edge-tts | "tscircuit" sometimes OK but inconsistent across voices; forcing letters is safe |+| `JLCPCB` | `J L C P C B` | edge-tts, azure | Acronym, always spell out |+| `PCB` | `P C B` | all | Acronym |+| `SMT` / `SMD` | `S M T` / `S M D` | all | Acronym |+| `KiCad` | `kai cad` | edge-tts | Some voices say "kee cad"; `kai cad` is the community pronunciation |+| `MPN` | `M P N` | all | Acronym |+| `BOM` | `B O M` or `bill of materials` | all | "bom" gets read as the word "bomb" by some voices; spelling out is safer |+| `FPGA` | `F P G A` | all | Acronym |+| `I²C` / `I2C` | `I squared C` or `I two C` | all | Superscript/digit both mangled |+| `SPI` | `S P I` | all | Acronym |+| `UART` | `you art` | all | Engines try to read as word (rhymes with "heart") which is wrong |+| `MCU` | `M C U` | all | Acronym |+| `GPIO` | `G P I O` | all | Acronym |+| Version numbers like `1.3.7` | `one point three point seven` | all | `1.3.7` gets read as "one three seven" or mangled decimals; always spell |+| Dates like `2026-04-23` | `April twenty third` (or "April twenty third twenty twenty six") | all | Hyphenated date gets mangled |+| Slugs / UUIDs | don't narrate them; reference as "the container" / "the workspace" | — | Never put a slug/UUID in a TTS stream |++## How to add an entry++Anyone can propose a new entry — the table lives in gallia and deploys via `gallia/install.mjs`. Contribution flow:++1. **Verify the problem.** Render the current pronunciation to confirm it's actually wrong:++    ```bash+    edge-tts --voice en-US-AndrewMultilingualNeural \+      --text "this is <your term> version one" \+      --write-media /tmp/_tts-before.mp3+    # Listen: does the TTS say the term the way a human would?+    ```++2. **Find a spelling that fixes it.** Common patterns:+    - Acronym → individual letters with spaces: `JLCPCB` → `J L C P C B`+    - Word with silent/weird letters → phonetic: `KiCad` → `kai cad`+    - Number pattern → words: `1.3.7` → `one point three point seven`+    - Hyphenated brand name → space-or-phonetic: `adom-tsci` → `adom t s c i`++3. **Verify the fix.** Render with the new spelling:++    ```bash+    edge-tts --voice en-US-AndrewMultilingualNeural \+      --text "this is <your phonetic spelling> version one" \+      --write-media /tmp/_tts-after.mp3+    # Confirm it now reads correctly.+    ```++4. **Add to `pronunciations.json`.** One entry per term:++    ```json+    {+      "written": "JLCPCB",+      "narration": "J L C P C B",+      "engines_confirmed": ["edge-tts", "azure"],+      "reason": "Acronym; reads as garbled single word",+      "added_by": "john",+      "added_date": "2026-04-23"+    }+    ```++5. **Commit + publish.** This skill lives inside the adom-tts repo (skills/tts-pronunciation/). To ship a table change, bump adom-tts's version and publish it per publish-skills/adom-tts-publish — every installer gets the update with the app.++## Engines we've tested against++- `edge-tts` (Microsoft Edge neural) — default on the platform, invoked as `edge-tts --voice <voice> --text <text> --write-media <file>`. Voice table:+    - `en-US-AndrewMultilingualNeural` — default for Adom demos (clear, neutral-male)+    - `en-US-AriaNeural` — polished female+    - `en-US-GuyNeural` — warm neutral-male+- `piper` — local offline TTS, fires on the platform when no network.+- `azure-tts` — via Microsoft Azure Speech SDK.+- `eleven-labs` — premium quality, used for hero demos.++Each engine has slightly different parsing rules. If a spelling works in one but not another, add a per-engine note in the `pronunciations.json` entry and pick the most permissive spelling (or provide per-engine overrides).++## Integration — skills that consult this table++The following skills (should) look up terms here before drafting narration. If you spot drift between their embedded tables and this one, this file wins:++- `demo-recording` — Step 2 (write the demo script with narration column)+- `video-post` — storyboard review phase, narration validation+- `voiceover` (when that flow ships) — pre-render check+- Any custom narration script a user writes++## One-liner verify in your own narration++Before rendering a whole 13-clip tour, pipe each scene's narration column through a verifier:++```bash+for narration in "$(jq -r '.scenes[].narration' demo/<name>-demo-script.json)"; do+  tmp=$(mktemp --suffix=.mp3)+  edge-tts --voice en-US-AndrewMultilingualNeural --text "$narration" --write-media "$tmp"+  echo "play: $tmp"+  # Listen or pipe to ffprobe for duration check+done+```++Cheap pre-flight; catches pronunciation and duration issues before you burn render time.+

@@ -0,0 +1,151 @@+{+  "$schema_comment": "Canonical TTS pronunciation table. Each entry: 'written' is how the term appears in captions/docs/code; 'narration' is the spelling fed to the TTS engine; 'engines_confirmed' lists which engines were tested; 'reason' and 'added_by' are metadata. Consumer skills (demo-recording, video-post, voiceover) look up the 'written' key and substitute 'narration' into any TTS input.",+  "version": "1.0.0",+  "updated": "2026-04-23",+  "entries": [+    {+      "written": "adom-tsci",+      "narration": "adom t s c i",+      "engines_confirmed": ["edge-tts"],+      "reason": "TTS reads 'tsci' as 'sci' or 'ski' — a single word. Spelling each letter with spaces gets the intended four-letter reading.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "tscircuit",+      "narration": "t s circuit",+      "engines_confirmed": ["edge-tts"],+      "reason": "Inconsistent across voices; some render 'tscircuit' correctly, others as 'tuh-circuit' or 'ts-circuit'. Safer to force letters.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "JLCPCB",+      "narration": "J L C P C B",+      "engines_confirmed": ["edge-tts", "azure"],+      "reason": "Acronym — reads as garbled single word without letter separation.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "PCB",+      "narration": "P C B",+      "engines_confirmed": ["edge-tts", "piper", "azure"],+      "reason": "Acronym, always spelled.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "SMT",+      "narration": "S M T",+      "engines_confirmed": ["edge-tts", "piper", "azure"],+      "reason": "Acronym (surface-mount technology).",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "SMD",+      "narration": "S M D",+      "engines_confirmed": ["edge-tts", "piper", "azure"],+      "reason": "Acronym (surface-mount device).",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "KiCad",+      "narration": "kai cad",+      "engines_confirmed": ["edge-tts"],+      "reason": "Community pronunciation is 'kai cad' (long-i); some voices default to 'kee cad'. Forcing the phonetic spelling matches the community norm.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "MPN",+      "narration": "M P N",+      "engines_confirmed": ["edge-tts", "azure"],+      "reason": "Acronym (manufacturer part number).",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "BOM",+      "narration": "bill of materials",+      "engines_confirmed": ["edge-tts", "piper"],+      "reason": "'BOM' reads as the word 'bomb' in many voices. 'B O M' also reads oddly because of the mouth-shape. Expanding to 'bill of materials' is cleanest.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "FPGA",+      "narration": "F P G A",+      "engines_confirmed": ["edge-tts", "piper", "azure"],+      "reason": "Acronym (field-programmable gate array).",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "I²C",+      "narration": "I squared C",+      "engines_confirmed": ["edge-tts"],+      "reason": "Superscript '²' gets dropped or mangled. 'I squared C' is the engineer-standard reading.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "I2C",+      "narration": "I squared C",+      "engines_confirmed": ["edge-tts"],+      "reason": "ASCII-fallback for I²C — same audio reading, match the standard spoken form.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "SPI",+      "narration": "S P I",+      "engines_confirmed": ["edge-tts", "piper"],+      "reason": "Acronym (serial peripheral interface). Engines otherwise try 'spy'.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "UART",+      "narration": "you art",+      "engines_confirmed": ["edge-tts"],+      "reason": "Engineers say 'you-art' (two syllables). Engines tend to rhyme it with 'heart' ('yoo-art' as one syllable). Forcing 'you art' with a space reproduces the intended split.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "MCU",+      "narration": "M C U",+      "engines_confirmed": ["edge-tts", "piper"],+      "reason": "Acronym (microcontroller unit).",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "GPIO",+      "narration": "G P I O",+      "engines_confirmed": ["edge-tts", "piper"],+      "reason": "Acronym (general-purpose input/output). Some voices try 'jee-pee-oh' with a blended i/o; letter-by-letter is cleaner.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "VERSION_NUMBER_PATTERN",+      "narration": "spell as words — e.g. '1.3.7' → 'one point three point seven'",+      "engines_confirmed": ["edge-tts", "piper", "azure"],+      "reason": "Numeric version strings like '1.3.7' get read as 'one three seven' or mangled decimals. Always spell in narration.",+      "added_by": "john",+      "added_date": "2026-04-23"+    },+    {+      "written": "DATE_PATTERN",+      "narration": "spell as words — e.g. '2026-04-23' → 'April twenty third'",+      "engines_confirmed": ["edge-tts", "piper"],+      "reason": "Hyphenated dates mangle. Convert to spoken form.",+      "added_by": "john",+      "added_date": "2026-04-23"+    }+  ]+}