Spanish API

Spanish G2P provides rule-based phoneme conversion for Spanish, designed for Kokoro TTS models.

Main Class

class kokorog2p.es.SpanishG2P(language: str = 'es', use_espeak_fallback: bool = False, use_goruut_fallback: bool = False, use_spacy: bool = False, spacy_model: str = 'es_core_news_sm', mark_stress: bool = True, dialect: str = 'es', expand_abbreviations: bool = True, enable_context_detection: bool = True, version: str = '1.0', **kwargs: Any)

Bases: G2PBase

Spanish G2P converter using rule-based phonemization.

This class provides grapheme-to-phoneme conversion for Spanish text using Spanish orthographic rules. Spanish has fairly regular spelling, making rule-based conversion quite accurate.

Example:

>>> g2p = SpanishG2P()
>>> tokens = g2p("Hola, ¿cómo estás?")
>>> for token in tokens:
...     print(f"{token.text} -> {token.phonemes}")

__init__(language: str = 'es', use_espeak_fallback: bool = False, use_goruut_fallback: bool = False, use_spacy: bool = False, spacy_model: str = 'es_core_news_sm', mark_stress: bool = True, dialect: str = 'es', expand_abbreviations: bool = True, enable_context_detection: bool = True, version: str = '1.0', **kwargs: Any) → None

Initialize the Spanish G2P converter.

Args:

language: Language code (default: ‘es’). use_espeak_fallback: Reserved for future espeak integration. use_goruut_fallback: Reserved for future goruut integration. use_spacy: Whether to use spaCy for tokenization and POS tagging.

Defaults to False to preserve existing behavior.

spacy_model: spaCy Spanish model package to load when use_spacy=True

(e.g., “es_core_news_sm”, “es_core_news_md”, “es_core_news_lg”).

mark_stress: Whether to mark primary stress with ˈ. dialect: “es” for European Spanish (with θ), “la” for Latin American (θ→s). expand_abbreviations: Whether to expand common abbreviations. enable_context_detection: Context-aware abbreviation expansion. version: Target model version.

__call__(text: str) → list[GToken]

Convert text to a list of tokens with phonemes.

Args:

text: Input text to convert.

Returns:

List of GToken objects with phonemes assigned.

property nlp: object

Lazily initialize spaCy.

property spacy_tokenizer: SpacyTokenizer

Lazily initialize the spaCy tokenizer.

lookup(word: str, tag: str | None = None) → str | None

Look up a word’s phonemes.

Args:

word: The word to look up. tag: Optional POS tag (ignored for Spanish).

Returns:

Phoneme string or None.

phonemize(text: str) → str

Convert text to phonemes.

Args:

text: Input text to convert.

Returns:

Phoneme string.

get_target_model() → str

Get the target Kokoro model variant for this G2P instance.

Returns:

Model identifier: version string (“1.1” or “1.0”).

Examples

from kokorog2p.es import SpanishG2P

g2p = SpanishG2P(language="es-es")
tokens = g2p("¡Hola mundo!")

for token in tokens:
    print(f"{token.text} -> {token.phonemes}")

Phonology Features

Spanish phonology includes:

• 5 pure vowels (a, e, i, o, u) - always pronounced clearly

• No vowel reduction (unlike English)

• Predictable stress (penultimate for vowel-ending words, final for consonant-ending)

• Palatal sounds: ñ [ɲ], ll [ʎ] (or [j] in most dialects), ch [ʧ]

• Jota: j/g+e/i [x]

• Theta: z/c+e/i [θ] in European Spanish (or [s] in Latin America)

• Tap vs trill: r [ɾ] vs rr/initial r [r]

• No consonant clusters simplification