misaki

What it is and what it does

This package is a grapheme-to-phoneme (G2P) engine that takes written text and produces phonetic transcriptions in IPA notation for text-to-speech synthesis. It supports five languages (English, Japanese, Korean, Chinese, Vietnamese) with language-specific tokenization pipelines: English uses spaCy and num2words; Japanese leverages pyopenjtalk with pitch accent support; Korean adapts g2pkc; Chinese uses jieba and pinyin conversion; Vietnamese relies on Viphoneme.

The core workflow is simple: instantiate a language-specific G2P object, pass text through it, and receive both phoneme sequences and token alignments. You can run without transformers for speed or enable transformer-based processing for context-aware disambiguation. Optional fallback to espeak handles out-of-vocabulary words. With only two runtime dependencies (addict and regex) and a pure-Python wheel, installation is straightforward, though language-specific extras must be selected at install time.

Use it for:

• Build multilingual TTS pipelines by converting text to phonemes for speech synthesis models.
• Preprocess text corpora for phonetic analysis or linguistic research across multiple languages.
• Handle out-of-vocabulary words in speech synthesis by falling back to espeak when dictionary lookup fails.
• Disambiguate homographs using optional transformer-based context when trf=True.
• Generate phonetic training data for speech models by batch-converting text documents to aligned phoneme sequences.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Converts written text to phonetic representations (grapheme-to-phoneme conversion) for text-to-speech systems, supporting English, Japanese, Korean, Chinese, and Vietnamese with language-specific tokenization and phoneme rules.

Yes, if you need multilingual grapheme-to-phoneme conversion for text-to-speech. The package is permissively licensed under Apache License Version 2.0, has low install friction, and covers five languages with specialized tokenization. However, the aging maintenance status (last release 496 days ago) means you should verify that the language and features you need are stable and that any issues may see slow response.

Install

misaki on PyPI

pip install misaki

uv add misaki

poetry add misaki

Installing misaki

Before you install

Low install friction with only two runtime dependencies (addict and regex). Maintenance status is aging—last release was 496 days ago—so expect slower response to issues, though the package appears stable for its current use case.

License in practice

Licensed under Apache License Version 2.0 (permissive), allowing free use, modification, and distribution with minimal restrictions; suitable for both open-source and commercial projects provided you include license attribution.

Quickstart

pip install "misaki[en]"

from misaki import en

g2p = en.G2P(trf=False, british=False, fallback=None)
text = 'Text to convert to phonemes.'
phonemes, tokens = g2p(text)
print(phonemes)

Language-specific extras (e.g., [en], [ja], [ko], [zh], [vi]) must be installed; optional fallback to espeak requires system-level installation of espeak-ng.

Verify before relying

• Performance characteristics (latency, throughput) for typical text lengths and batch sizes.
• Accuracy metrics or benchmarks against reference datasets.
• Whether transformer-based mode (trf=True) requires additional dependencies or model downloads.
• Compatibility and behavior with out-of-vocabulary or mixed-language text.
• Current state of language-specific features (pitch accent for Japanese, etc.) relative to the description.

Package facts

Evidence: misaki-0.9.4-py3-none-any.whl

Tags

More Linguistic packages