Sinhala (සිංහල) review centers on this evidence: check Sinhala vowel signs, conjunct forms, inflected endings, names, numbers, and Sinhala–English switches. For underspecified si, CLDR supplies Sinh (Sinhala script) as a likely/default web-locale hint—not an audio attribute or exclusive Sinhala orthography. Confirm the actual orthography and script with the project owner before normalizing any text. Orthographic targets include vowel signs, conjunct forms, word boundaries, names, and mixed-language passages. Project decision: which Sinhala spelling and treatment of English technical names applies. Before batch editing si, a reviewer must record which Sinhala spelling and treatment of English technical names applies and attach a source timestamp to disputed text.
Where this workflow fits
- Sinhala interviews and oral histories
- Sinhala lectures and training recordings
- Source-linked Sinhala research review
Sinhala orthography and speech checkpoints
check Sinhala vowel signs, conjunct forms, inflected endings, names, numbers, and Sinhala–English switches. Editorial decision: which Sinhala spelling and treatment of English technical names applies. Visual inspection should cover record the project decision about which Sinhala spelling and treatment of English technical names applies.
Script choice and source-linked review for සිංහල
For underspecified si, CLDR supplies Sinh (Sinhala script) as a likely/default web-locale hint—not an audio attribute or exclusive Sinhala orthography. Confirm the actual orthography and script with the project owner before normalizing any text. For multilingual interviews with names, honorifics, and English code-switching, inspect check Sinhala vowel signs, conjunct forms, inflected endings, names, numbers, and Sinhala–English switches. Visually inspect vowel signs, conjunct forms, word boundaries, names, and mixed-language passages; record the project decision about which Sinhala spelling and treatment of English technical names applies. Replay a complete clause around every uncertain name, quantity, interruption, or ending.
Frozen deployment boundary
This page is published only because its language is present in capability snapshot m10-2026-07-20.1. It does not extend that catalog or claim a measured accuracy score.
- The si hint maps to the reviewed si provider root and preserves si as the user's transcript language tag.
- CLDR Sinh is a likely/default locale hint, not an audio property; capability flags remain per language and model while editors confirm the project's real script and orthography.
Reviewed provider capability
assemblyai · universal-2
root si · tiers fast, standard, precision
- Automatic detection
- Reviewed no
- Diarization
- Reviewed no
- Word timestamps
- Reviewed yes
Questions from the workflow
What must a Sinhala editor decide before correcting the transcript?
vowel signs, consonant clusters, inflected forms, names, and borrowed speech should follow the selected standard rather than an automatic transliteration. For Sinhala, check Sinhala vowel signs, conjunct forms, inflected endings, names, numbers, and Sinhala–English switches. Project choice: which Sinhala spelling and treatment of English technical names applies. Keep unresolved forms beside their source timestamps.
Reviewed sources
- IANA Language Subtag Registry · checked 2026-07-20
- AssemblyAI model and supported-language documentation · checked 2026-07-20
- AssemblyAI pre-recorded audio supported languages · checked 2026-07-20
- Unicode CLDR likely-subtags language and script data · checked 2026-07-20
- Sinhala language and orthography editorial reference · checked 2026-07-20
- World Atlas of Language Structures Online · checked 2026-07-20