orthography2ipa
Linguistically motivated grapheme-to-IPA and allophone mappings for 350+ language codes
Decision gist · record as of 2026-08-14
Yes, if you need IPA transcription or language similarity metrics for research or NLP. The library is actively maintained, has no known vulnerabilities, and covers a broad language base. The Alpha status and early release history mean the API and data specs may shift; verify transcription accuracy for your specific languages before production use. Low install friction and permissive licensing make it a low-risk addition.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- Active maintenance with a recent release (29 days old).
- Low install friction: pure Python wheel with three runtime dependencies (numpy, langcodes, ovos-spec-tools).
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with attribution and liability disclaimers. No copyleft obligations.
last release 2026-07-16 (29 days) · last repo commit 2026-08-14 · 1 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 107,342 downloads/mo, #12,617 on PyPI
Alternatives
Verify before relying
pip install orthography2ipa
import orthography2ipa
result = orthography2ipa.transcribe("olá mundo", "pt")
print(result) # 'oˈla ˈmũdu'- Actual accuracy of IPA transcriptions across the 676 supported languages and dialects.
- Performance characteristics when processing large text volumes or many languages.
- Stability of the API and data format given the Alpha development status.
What it is and what it does
orthography2ipa is a linguistically motivated library for converting written text to IPA phonetic notation and measuring how languages relate to each other. It ships with data specs for 676 languages and 73 clade nodes covering major language families, reconstructed proto-languages, dialects, and creoles. Rather than learning phoneme-to-sound mappings from weights, the library uses declarative per-language JSON specs that define graphemes, phonemes, allophones, positional rules, and genealogical metadata. A shared, language-agnostic engine applies these specs to produce transcriptions and confidence scores.
The library's core insight is that language similarity is multidimensional: two languages can sound alike but write differently, or vice versa. It measures each axis independently—phonological inventory overlap, how the same text sounds across languages, how the same sounds are spelled, script typology, ancestry, temporal span, and geographic distance. When spelling is ambiguous, the engine builds a ranked lattice of possible pronunciations with costs, allowing downstream systems to refine choices via custom rescoring rules. It also handles edge cases like logographic scripts (Chinese Hanzi has no grapheme map but a full phonology) and reconstructed languages (Proto-Indo-European declares its phonemes directly).
Use it for
- Transcribe text to IPA for linguistic research, speech synthesis, or phonetic analysis across hundreds of language varieties.
- Measure phonological and orthographic distance between language pairs to study mutual intelligibility or dialect relationships.
- Build multilingual text-to-speech systems that need per-language grapheme-to-phoneme rules without training separate models.
- Analyze how spelling conventions diverge from pronunciation in a single language or across related languages.
- Refine ambiguous transcriptions using custom rescoring rules for domain-specific or specialized phonetic contexts.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need IPA transcription or language similarity metrics for research or NLP.
The library is actively maintained, has no known vulnerabilities, and covers a broad language base. The Alpha status and early release history mean the API and data specs may shift; verify transcription accuracy for your specific languages before production use. Low install friction and permissive licensing make it a low-risk addition.
Install
orthography2ipa on PyPI
Before you install
Active maintenance with a recent release (29 days old). Low install friction: pure Python wheel with three runtime dependencies (numpy, langcodes, ovos-spec-tools). Supports current Python versions (3.10–3.13).
Requires Python 3.10 or later.
License in practice
Apache-2.0 permissive license allows commercial and private use with attribution and liability disclaimers. No copyleft obligations.
Quickstart
pip install orthography2ipa
import orthography2ipa
result = orthography2ipa.transcribe("olá mundo", "pt")
print(result) # 'oˈla ˈmũdu'Verify before relying
- Actual accuracy of IPA transcriptions across the 676 supported languages and dialects.
- Performance characteristics when processing large text volumes or many languages.
- Stability of the API and data format given the Alpha development status.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packagesnumpylangcodesovos-spec-tools |
| Maintenance | Actively maintained 29 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 107,342 / month, #12,617 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 3 - AlphaIntended Audience :: DevelopersIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Topic :: Text Processing :: Linguistic |
Evidence: orthography2ipa-7.30.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “grapheme to IPA transcription”
- orthography2ipaConverts spelling to IPA phonetic transcription and measures language…
- epitranEpitran converts written text in various languages and scripts into…
- phonemizerPhonemizer converts written text into phonetic representations (IPA,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Linguistic packages
Detects and normalizes text encoding from unknown or ambiguous sources, supporting all IANA character sets that Python's core library provides codecs for, with the ability to register custom codecs.
tiktoken is a fast BPE tokenizer that converts text into token sequences compatible with OpenAI models, supporting multiple encoding schemes including o200k_base and model-specific encodings.
Install it if you work with OpenAI APIs or need to understand token boundaries in GPT-family models.
Detects character encoding and language in byte sequences with high accuracy, supporting 99 encodings and returning confidence scores, language tags, and MIME types.
Install it if you need to detect character encoding or language in byte data; the rewrite makes it substantially faster and more accurate than its predecessors.
Converts Unicode text to ASCII by transliterating non-ASCII characters into their closest ASCII equivalents, with no runtime dependencies.
However, if transliteration quality or ongoing maintenance matters, consider unidecode instead despite its GPL-only license.
Lark is a parsing library that builds abstract syntax trees from context-free grammars, supporting multiple parsing algorithms (Earley, LALR(1), CYK) with automatic line and column tracking.
Python bindings to the tree-sitter parsing library, enabling incremental parsing and syntax tree analysis for source code.
See also epitran · g2p-en · misaki · gruut-ipa · phonemizer · panphon · phonemizer-fork · gruut · gruut-lang-en · soundex