Create ipa_data.py

ipa_data.py

@@ -0,0 +1,776 @@
+"""
+IPA Data Module — Shared phoneme data for all IPA Hugging Face Spaces.
+
+Contains:
+- Full IPA consonant inventory with articulatory features
+- Full IPA vowel inventory with height/backness/rounding
+- Spanish phoneme annotations and example words
+- Chart layout constants (place/manner ordering, vowel trapezoid coordinates)
+"""
+
+# =============================================================================
+# CONSONANT CHART DATA
+# =============================================================================
+
+# Column order for the consonant chart (place of articulation)
+CONSONANT_PLACES = [
+    "bilabial",
+    "labiodental",
+    "dental",
+    "alveolar",
+    "postalveolar",
+    "retroflex",
+    "palatal",
+    "velar",
+    "uvular",
+    "pharyngeal",
+    "glottal",
+]
+
+# Row order for the consonant chart (manner of articulation)
+CONSONANT_MANNERS = [
+    "plosive",
+    "nasal",
+    "trill",
+    "tap/flap",
+    "fricative",
+    "lateral fricative",
+    "approximant",
+    "lateral approximant",
+]
+
+# Full IPA consonant data
+# Each entry: symbol -> {place, manner, voicing, name, spanish, spanish_example, espeak_code, languages}
+CONSONANTS = {
+    # === PLOSIVES ===
+    "p": {
+        "place": "bilabial", "manner": "plosive", "voicing": "voiceless",
+        "name": "voiceless bilabial plosive",
+        "spanish": True, "spanish_example": "padre",
+        "espeak_code": "p",
+        "languages": ["English", "Spanish", "French", "German", "Mandarin"],
+    },
+    "b": {
+        "place": "bilabial", "manner": "plosive", "voicing": "voiced",
+        "name": "voiced bilabial plosive",
+        "spanish": True, "spanish_example": "boca",
+        "espeak_code": "b",
+        "languages": ["English", "Spanish", "French", "Arabic"],
+    },
+    "t": {
+        "place": "alveolar", "manner": "plosive", "voicing": "voiceless",
+        "name": "voiceless alveolar plosive",
+        "spanish": True, "spanish_example": "taza",
+        "espeak_code": "t",
+        "languages": ["English", "Spanish", "French", "German"],
+    },
+    "d": {
+        "place": "alveolar", "manner": "plosive", "voicing": "voiced",
+        "name": "voiced alveolar plosive",
+        "spanish": True, "spanish_example": "dedo",
+        "espeak_code": "d",
+        "languages": ["English", "Spanish", "French", "Italian"],
+    },
+    "t\u0288": {  # ʈ
+        "place": "retroflex", "manner": "plosive", "voicing": "voiceless",
+        "name": "voiceless retroflex plosive",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "t.",
+        "languages": ["Hindi", "Swedish", "Norwegian"],
+    },
+    "\u0256": {  # ɖ
+        "place": "retroflex", "manner": "plosive", "voicing": "voiced",
+        "name": "voiced retroflex plosive",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "d.",
+        "languages": ["Hindi", "Tamil", "Swedish"],
+    },
+    "c": {
+        "place": "palatal", "manner": "plosive", "voicing": "voiceless",
+        "name": "voiceless palatal plosive",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "c",
+        "languages": ["Hungarian", "Turkish", "Greek"],
+    },
+    "\u025f": {  # ɟ
+        "place": "palatal", "manner": "plosive", "voicing": "voiced",
+        "name": "voiced palatal plosive",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "J",
+        "languages": ["Hungarian", "Turkish", "Latvian"],
+    },
+    "k": {
+        "place": "velar", "manner": "plosive", "voicing": "voiceless",
+        "name": "voiceless velar plosive",
+        "spanish": True, "spanish_example": "casa",
+        "espeak_code": "k",
+        "languages": ["English", "Spanish", "French", "German", "Mandarin"],
+    },
+    "\u0261": {  # ɡ
+        "place": "velar", "manner": "plosive", "voicing": "voiced",
+        "name": "voiced velar plosive",
+        "spanish": True, "spanish_example": "gato",
+        "espeak_code": "g",
+        "languages": ["English", "Spanish", "French", "German"],
+    },
+    "q": {
+        "place": "uvular", "manner": "plosive", "voicing": "voiceless",
+        "name": "voiceless uvular plosive",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "q",
+        "languages": ["Arabic", "Quechua", "Inuktitut"],
+    },
+    "\u0262": {  # ɢ
+        "place": "uvular", "manner": "plosive", "voicing": "voiced",
+        "name": "voiced uvular plosive",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": None,
+        "languages": ["Somali", "Inuktitut"],
+    },
+    "\u0294": {  # ʔ
+        "place": "glottal", "manner": "plosive", "voicing": "voiceless",
+        "name": "glottal stop",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "?",
+        "languages": ["English (uh-oh)", "Arabic", "Hawaiian", "German"],
+    },
+
+    # === NASALS ===
+    "m": {
+        "place": "bilabial", "manner": "nasal", "voicing": "voiced",
+        "name": "voiced bilabial nasal",
+        "spanish": True, "spanish_example": "madre",
+        "espeak_code": "m",
+        "languages": ["English", "Spanish", "French", "German", "Mandarin"],
+    },
+    "\u0271": {  # ɱ
+        "place": "labiodental", "manner": "nasal", "voicing": "voiced",
+        "name": "voiced labiodental nasal",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "M",
+        "languages": ["English (comfort)", "Italian", "Dutch"],
+    },
+    "n": {
+        "place": "alveolar", "manner": "nasal", "voicing": "voiced",
+        "name": "voiced alveolar nasal",
+        "spanish": True, "spanish_example": "noche",
+        "espeak_code": "n",
+        "languages": ["English", "Spanish", "French", "German", "Mandarin"],
+    },
+    "\u0273": {  # ɳ
+        "place": "retroflex", "manner": "nasal", "voicing": "voiced",
+        "name": "voiced retroflex nasal",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "n.",
+        "languages": ["Hindi", "Swedish", "Norwegian"],
+    },
+    "\u0272": {  # ɲ
+        "place": "palatal", "manner": "nasal", "voicing": "voiced",
+        "name": "voiced palatal nasal",
+        "spanish": True, "spanish_example": "niño (ñ)",
+        "espeak_code": "n^",
+        "languages": ["Spanish", "French (cognac)", "Italian", "Portuguese"],
+    },
+    "\u014b": {  # ŋ
+        "place": "velar", "manner": "nasal", "voicing": "voiced",
+        "name": "voiced velar nasal",
+        "spanish": True, "spanish_example": "tengo (before g/k)",
+        "espeak_code": "N",
+        "languages": ["English (sing)", "Spanish", "German", "Mandarin"],
+    },
+    "\u0274": {  # ɴ
+        "place": "uvular", "manner": "nasal", "voicing": "voiced",
+        "name": "voiced uvular nasal",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": None,
+        "languages": ["Japanese", "Inuktitut"],
+    },
+
+    # === TRILLS ===
+    "\u0299": {  # ʙ
+        "place": "bilabial", "manner": "trill", "voicing": "voiced",
+        "name": "voiced bilabial trill",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": None,
+        "languages": ["Nias", "Titan"],
+    },
+    "r": {
+        "place": "alveolar", "manner": "trill", "voicing": "voiced",
+        "name": "voiced alveolar trill",
+        "spanish": True, "spanish_example": "perro",
+        "espeak_code": "r",
+        "languages": ["Spanish", "Italian", "Russian", "Arabic"],
+    },
+    "\u0280": {  # ʀ
+        "place": "uvular", "manner": "trill", "voicing": "voiced",
+        "name": "voiced uvular trill",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "R",
+        "languages": ["French", "German", "Dutch"],
+    },
+
+    # === TAPS / FLAPS ===
+    "\u2c71": {  # ⱱ
+        "place": "labiodental", "manner": "tap/flap", "voicing": "voiced",
+        "name": "voiced labiodental flap",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": None,
+        "languages": ["Mono", "some Central African languages"],
+    },
+    "\u027e": {  # ɾ
+        "place": "alveolar", "manner": "tap/flap", "voicing": "voiced",
+        "name": "voiced alveolar tap",
+        "spanish": True, "spanish_example": "pero",
+        "espeak_code": "*",
+        "languages": ["Spanish", "Japanese", "Korean", "Portuguese"],
+    },
+    "\u027d": {  # ɽ
+        "place": "retroflex", "manner": "tap/flap", "voicing": "voiced",
+        "name": "voiced retroflex flap",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "*.",
+        "languages": ["Hindi", "Urdu", "Hausa"],
+    },
+
+    # === FRICATIVES ===
+    "\u0278": {  # ɸ
+        "place": "bilabial", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless bilabial fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "F",
+        "languages": ["Japanese (fu)", "Ewe"],
+    },
+    "\u03b2": {  # β
+        "place": "bilabial", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced bilabial fricative",
+        "spanish": True, "spanish_example": "lobo (allophone of /b/)",
+        "espeak_code": "B",
+        "languages": ["Spanish (allophone)", "Ewe", "Japanese"],
+    },
+    "f": {
+        "place": "labiodental", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless labiodental fricative",
+        "spanish": True, "spanish_example": "fuego",
+        "espeak_code": "f",
+        "languages": ["English", "Spanish", "French", "German"],
+    },
+    "v": {
+        "place": "labiodental", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced labiodental fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "v",
+        "languages": ["English", "French", "German", "Russian"],
+    },
+    "\u03b8": {  # θ
+        "place": "dental", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless dental fricative",
+        "spanish": True, "spanish_example": "zapato (Castilian)",
+        "espeak_code": "T",
+        "languages": ["English (think)", "Spanish (Castilian)", "Greek"],
+    },
+    "\u00f0": {  # ð
+        "place": "dental", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced dental fricative",
+        "spanish": True, "spanish_example": "dedo (allophone of /d/)",
+        "espeak_code": "D",
+        "languages": ["English (the)", "Spanish (allophone)", "Icelandic"],
+    },
+    "s": {
+        "place": "alveolar", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless alveolar fricative",
+        "spanish": True, "spanish_example": "sol",
+        "espeak_code": "s",
+        "languages": ["English", "Spanish", "French", "German", "Mandarin"],
+    },
+    "z": {
+        "place": "alveolar", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced alveolar fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "z",
+        "languages": ["English", "French", "Italian", "Russian"],
+    },
+    "\u0283": {  # ʃ
+        "place": "postalveolar", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless postalveolar fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "S",
+        "languages": ["English (ship)", "French (chat)", "German (schön)"],
+    },
+    "\u0292": {  # ʒ
+        "place": "postalveolar", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced postalveolar fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "Z",
+        "languages": ["English (measure)", "French (je)", "Portuguese"],
+    },
+    "\u0282": {  # ʂ
+        "place": "retroflex", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless retroflex fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "s.",
+        "languages": ["Mandarin (sh)", "Polish", "Sanskrit"],
+    },
+    "\u0290": {  # ʐ
+        "place": "retroflex", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced retroflex fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "z.",
+        "languages": ["Mandarin (r-)", "Polish", "Russian"],
+    },
+    "\u00e7": {  # ç
+        "place": "palatal", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless palatal fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "C",
+        "languages": ["German (ich)", "Greek", "Japanese (hi)"],
+    },
+    "\u029d": {  # ʝ
+        "place": "palatal", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced palatal fricative",
+        "spanish": True, "spanish_example": "mayo (some dialects)",
+        "espeak_code": "j",
+        "languages": ["Spanish (some dialects)", "Greek", "Irish"],
+    },
+    "x": {
+        "place": "velar", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless velar fricative",
+        "spanish": True, "spanish_example": "jota",
+        "espeak_code": "x",
+        "languages": ["Spanish", "German (Bach)", "Russian", "Arabic"],
+    },
+    "\u0263": {  # ɣ
+        "place": "velar", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced velar fricative",
+        "spanish": True, "spanish_example": "lago (allophone of /g/)",
+        "espeak_code": "Q",
+        "languages": ["Spanish (allophone)", "Greek", "Irish"],
+    },
+    "\u03c7": {  # χ
+        "place": "uvular", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless uvular fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "X",
+        "languages": ["German (some dialects)", "Hebrew", "Welsh"],
+    },
+    "\u0281": {  # ʁ
+        "place": "uvular", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced uvular fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "g\"",
+        "languages": ["French (r)", "German (r)", "Dutch"],
+    },
+    "\u0127": {  # ħ
+        "place": "pharyngeal", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless pharyngeal fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "H",
+        "languages": ["Arabic (ح)", "Hebrew", "Somali"],
+    },
+    "\u0295": {  # ʕ
+        "place": "pharyngeal", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced pharyngeal fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "Q\"",
+        "languages": ["Arabic (ع)", "Hebrew", "Somali"],
+    },
+    "h": {
+        "place": "glottal", "manner": "fricative", "voicing": "voiceless",
+        "name": "voiceless glottal fricative",
+        "spanish": True, "spanish_example": "huevo (some dialects)",
+        "espeak_code": "h",
+        "languages": ["English", "German", "Japanese", "Arabic"],
+    },
+    "\u0266": {  # ɦ
+        "place": "glottal", "manner": "fricative", "voicing": "voiced",
+        "name": "voiced glottal fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "h\\",
+        "languages": ["Dutch", "Czech", "Ukrainian"],
+    },
+
+    # === LATERAL FRICATIVES ===
+    "\u026c": {  # ɬ
+        "place": "alveolar", "manner": "lateral fricative", "voicing": "voiceless",
+        "name": "voiceless alveolar lateral fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "l#",
+        "languages": ["Welsh (ll)", "Zulu", "Navajo"],
+    },
+    "\u026e": {  # ɮ
+        "place": "alveolar", "manner": "lateral fricative", "voicing": "voiced",
+        "name": "voiced alveolar lateral fricative",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": None,
+        "languages": ["Mongolian", "Zulu"],
+    },
+
+    # === APPROXIMANTS ===
+    "\u028b": {  # ʋ
+        "place": "labiodental", "manner": "approximant", "voicing": "voiced",
+        "name": "voiced labiodental approximant",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "v#",
+        "languages": ["Dutch", "Finnish", "Hindi"],
+    },
+    "\u0279": {  # ɹ
+        "place": "alveolar", "manner": "approximant", "voicing": "voiced",
+        "name": "voiced alveolar approximant",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "r\\",
+        "languages": ["English (red)", "some Dutch dialects"],
+    },
+    "\u027b": {  # ɻ
+        "place": "retroflex", "manner": "approximant", "voicing": "voiced",
+        "name": "voiced retroflex approximant",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "r\\.",
+        "languages": ["Tamil", "American English (r)"],
+    },
+    "j": {
+        "place": "palatal", "manner": "approximant", "voicing": "voiced",
+        "name": "voiced palatal approximant",
+        "spanish": True, "spanish_example": "yo (some dialects)",
+        "espeak_code": "j\\",
+        "languages": ["English (yes)", "Spanish", "French", "German"],
+    },
+    "w": {
+        "place": "velar", "manner": "approximant", "voicing": "voiced",
+        "name": "voiced labial-velar approximant",
+        "spanish": True, "spanish_example": "huevo",
+        "espeak_code": "w",
+        "languages": ["English", "Spanish", "French", "Mandarin"],
+    },
+
+    # === LATERAL APPROXIMANTS ===
+    "l": {
+        "place": "alveolar", "manner": "lateral approximant", "voicing": "voiced",
+        "name": "voiced alveolar lateral approximant",
+        "spanish": True, "spanish_example": "luna",
+        "espeak_code": "l",
+        "languages": ["English", "Spanish", "French", "German"],
+    },
+    "\u026d": {  # ɭ
+        "place": "retroflex", "manner": "lateral approximant", "voicing": "voiced",
+        "name": "voiced retroflex lateral approximant",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "l.",
+        "languages": ["Tamil", "Hindi", "Norwegian"],
+    },
+    "\u028e": {  # ʎ
+        "place": "palatal", "manner": "lateral approximant", "voicing": "voiced",
+        "name": "voiced palatal lateral approximant",
+        "spanish": True, "spanish_example": "calle (traditional)",
+        "espeak_code": "l^",
+        "languages": ["Spanish (traditional)", "Italian", "Portuguese", "Catalan"],
+    },
+    "\u029f": {  # ʟ
+        "place": "velar", "manner": "lateral approximant", "voicing": "voiced",
+        "name": "voiced velar lateral approximant",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "L",
+        "languages": ["Mid-Waghi", "some PNG languages"],
+    },
+}
+
+
+# =============================================================================
+# VOWEL CHART DATA
+# =============================================================================
+
+# Vowel height levels (top to bottom)
+VOWEL_HEIGHTS = ["close", "near-close", "close-mid", "mid", "open-mid", "near-open", "open"]
+
+# Vowel backness levels (left to right)
+VOWEL_BACKNESSES = ["front", "central", "back"]
+
+# Full IPA vowel data
+VOWELS = {
+    # === CLOSE VOWELS ===
+    "i": {
+        "height": "close", "backness": "front", "rounding": "unrounded",
+        "name": "close front unrounded vowel",
+        "spanish": True, "spanish_example": "sí",
+        "espeak_code": "i",
+        "languages": ["English (see)", "Spanish", "French", "German"],
+    },
+    "y": {
+        "height": "close", "backness": "front", "rounding": "rounded",
+        "name": "close front rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "y",
+        "languages": ["French (tu)", "German (über)", "Finnish", "Mandarin (ü)"],
+    },
+    "\u0268": {  # ɨ
+        "height": "close", "backness": "central", "rounding": "unrounded",
+        "name": "close central unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "i\"",
+        "languages": ["Russian (ы)", "Polish", "Romanian"],
+    },
+    "\u0289": {  # ʉ
+        "height": "close", "backness": "central", "rounding": "rounded",
+        "name": "close central rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "u\"",
+        "languages": ["Swedish", "Norwegian", "some English dialects"],
+    },
+    "\u026f": {  # ɯ
+        "height": "close", "backness": "back", "rounding": "unrounded",
+        "name": "close back unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "u-",
+        "languages": ["Turkish", "Japanese", "Korean"],
+    },
+    "u": {
+        "height": "close", "backness": "back", "rounding": "rounded",
+        "name": "close back rounded vowel",
+        "spanish": True, "spanish_example": "tú",
+        "espeak_code": "u",
+        "languages": ["English (boot)", "Spanish", "French", "German"],
+    },
+
+    # === NEAR-CLOSE VOWELS ===
+    "\u026a": {  # ɪ
+        "height": "near-close", "backness": "front", "rounding": "unrounded",
+        "name": "near-close front unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "I",
+        "languages": ["English (bit)", "German"],
+    },
+    "\u028f": {  # ʏ
+        "height": "near-close", "backness": "front", "rounding": "rounded",
+        "name": "near-close front rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "Y",
+        "languages": ["German (hübsch)", "Swedish"],
+    },
+    "\u028a": {  # ʊ
+        "height": "near-close", "backness": "back", "rounding": "rounded",
+        "name": "near-close back rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "U",
+        "languages": ["English (book)", "German"],
+    },
+
+    # === CLOSE-MID VOWELS ===
+    "e": {
+        "height": "close-mid", "backness": "front", "rounding": "unrounded",
+        "name": "close-mid front unrounded vowel",
+        "spanish": True, "spanish_example": "mesa",
+        "espeak_code": "e",
+        "languages": ["Spanish", "French (été)", "German (Beet)", "Italian"],
+    },
+    "\u00f8": {  # ø
+        "height": "close-mid", "backness": "front", "rounding": "rounded",
+        "name": "close-mid front rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "Y\"",
+        "languages": ["French (peu)", "German (schön)", "Danish", "Finnish"],
+    },
+    "\u0258": {  # ɘ
+        "height": "close-mid", "backness": "central", "rounding": "unrounded",
+        "name": "close-mid central unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": None,
+        "languages": ["Korean", "Paicî"],
+    },
+    "\u0275": {  # ɵ
+        "height": "close-mid", "backness": "central", "rounding": "rounded",
+        "name": "close-mid central rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": None,
+        "languages": ["Swedish", "Australian English"],
+    },
+    "\u0264": {  # ɤ
+        "height": "close-mid", "backness": "back", "rounding": "unrounded",
+        "name": "close-mid back unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "o-",
+        "languages": ["Korean", "Vietnamese", "Thai"],
+    },
+    "o": {
+        "height": "close-mid", "backness": "back", "rounding": "rounded",
+        "name": "close-mid back rounded vowel",
+        "spanish": True, "spanish_example": "como",
+        "espeak_code": "o",
+        "languages": ["Spanish", "French (beau)", "German (Boot)", "Italian"],
+    },
+
+    # === MID VOWEL ===
+    "\u0259": {  # ə (schwa)
+        "height": "mid", "backness": "central", "rounding": "unrounded",
+        "name": "mid central vowel (schwa)",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "@",
+        "languages": ["English (about)", "French (le)", "German (bitte)"],
+    },
+
+    # === OPEN-MID VOWELS ===
+    "\u025b": {  # ɛ
+        "height": "open-mid", "backness": "front", "rounding": "unrounded",
+        "name": "open-mid front unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "E",
+        "languages": ["English (bed)", "French (fête)", "Italian"],
+    },
+    "\u0153": {  # œ
+        "height": "open-mid", "backness": "front", "rounding": "rounded",
+        "name": "open-mid front rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "W",
+        "languages": ["French (peur)", "German (Hölle)"],
+    },
+    "\u025c": {  # ɜ
+        "height": "open-mid", "backness": "central", "rounding": "unrounded",
+        "name": "open-mid central unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "3",
+        "languages": ["English (bird - British)"],
+    },
+    "\u025e": {  # ɞ
+        "height": "open-mid", "backness": "central", "rounding": "rounded",
+        "name": "open-mid central rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": None,
+        "languages": ["Irish", "some English dialects"],
+    },
+    "\u028c": {  # ʌ
+        "height": "open-mid", "backness": "back", "rounding": "unrounded",
+        "name": "open-mid back unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "V",
+        "languages": ["English (but)", "Korean"],
+    },
+    "\u0254": {  # ɔ
+        "height": "open-mid", "backness": "back", "rounding": "rounded",
+        "name": "open-mid back rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "O",
+        "languages": ["English (thought)", "French (mort)", "Italian"],
+    },
+
+    # === NEAR-OPEN VOWELS ===
+    "\u00e6": {  # æ
+        "height": "near-open", "backness": "front", "rounding": "unrounded",
+        "name": "near-open front unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "a#",
+        "languages": ["English (cat)", "Danish", "Arabic"],
+    },
+    "\u0250": {  # ɐ
+        "height": "near-open", "backness": "central", "rounding": "unrounded",
+        "name": "near-open central vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "a\"",
+        "languages": ["German (bitter)", "Portuguese", "some English dialects"],
+    },
+
+    # === OPEN VOWELS ===
+    "a": {
+        "height": "open", "backness": "front", "rounding": "unrounded",
+        "name": "open front unrounded vowel",
+        "spanish": True, "spanish_example": "casa",
+        "espeak_code": "a",
+        "languages": ["Spanish", "French (patte)", "Italian", "German"],
+    },
+    "\u0276": {  # ɶ
+        "height": "open", "backness": "front", "rounding": "rounded",
+        "name": "open front rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": None,
+        "languages": ["Danish", "some German dialects"],
+    },
+    "\u0251": {  # ɑ
+        "height": "open", "backness": "back", "rounding": "unrounded",
+        "name": "open back unrounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "A",
+        "languages": ["English (father)", "French (pâte)", "Persian"],
+    },
+    "\u0252": {  # ɒ
+        "height": "open", "backness": "back", "rounding": "rounded",
+        "name": "open back rounded vowel",
+        "spanish": False, "spanish_example": None,
+        "espeak_code": "A.",
+        "languages": ["British English (lot)", "Hungarian"],
+    },
+}
+
+
+# =============================================================================
+# VOWEL TRAPEZOID COORDINATES (for SVG rendering)
+# =============================================================================
+
+# SVG viewBox: 0 0 500 400
+# The trapezoid is narrower at top (close) and wider at bottom (open)
+# x increases left-to-right (front → back), y increases top-to-bottom (close → open)
+VOWEL_TRAPEZOID_COORDS = {
+    # (x, y) positions on the trapezoid SVG
+    # Close row
+    ("close", "front"): (80, 40),
+    ("close", "central"): (250, 40),
+    ("close", "back"): (420, 40),
+    # Near-close row
+    ("near-close", "front"): (110, 95),
+    ("near-close", "back"): (400, 95),
+    # Close-mid row
+    ("close-mid", "front"): (130, 145),
+    ("close-mid", "central"): (255, 145),
+    ("close-mid", "back"): (380, 145),
+    # Mid row
+    ("mid", "central"): (260, 200),
+    # Open-mid row
+    ("open-mid", "front"): (170, 250),
+    ("open-mid", "central"): (265, 250),
+    ("open-mid", "back"): (360, 250),
+    # Near-open row
+    ("near-open", "front"): (195, 305),
+    ("near-open", "central"): (270, 305),
+    # Open row
+    ("open", "front"): (215, 355),
+    ("open", "back"): (340, 355),
+}
+
+
+# =============================================================================
+# HELPER FUNCTIONS
+# =============================================================================
+
+def get_consonant_at(place, manner, voicing):
+    """Get the IPA symbol for a consonant at a specific position in the chart."""
+    for symbol, data in CONSONANTS.items():
+        if data["place"] == place and data["manner"] == manner and data["voicing"] == voicing:
+            return symbol
+    return None
+
+
+def get_vowel_at(height, backness, rounding):
+    """Get the IPA symbol for a vowel at a specific position in the chart."""
+    for symbol, data in VOWELS.items():
+        if data["height"] == height and data["backness"] == backness and data["rounding"] == rounding:
+            return symbol
+    return None
+
+
+def get_spanish_consonants():
+    """Return all consonants that appear in Spanish."""
+    return {sym: data for sym, data in CONSONANTS.items() if data["spanish"]}
+
+
+def get_spanish_vowels():
+    """Return all vowels that appear in Spanish."""
+    return {sym: data for sym, data in VOWELS.items() if data["spanish"]}
+
+
+def get_all_spanish_phonemes():
+    """Return all Spanish phonemes (consonants + vowels)."""
+    return {**get_spanish_consonants(), **get_spanish_vowels()}
+
+
+def get_phoneme_info(symbol):
+    """Look up any IPA symbol and return its full data."""
+    if symbol in CONSONANTS:
+        return {"type": "consonant", **CONSONANTS[symbol]}
+    if symbol in VOWELS:
+        return {"type": "vowel", **VOWELS[symbol]}
+    return None