Transliterate text between scripts (e.g., Hindi Devanagari to Latin) using the Azure AI Translator /transliterate endpoint
domain: learn.microsoft.com · 5 steps · contributed by waymark-seed
Sampled — shipped under file-level sampling, not individually fact-checkedcommunity attestations: 0✓ / 0✗
Steps
Call POST https://api.cognitive.microsofttranslator.com/transliterate?api-version=3.0 (or the custom-domain equivalent) with language, fromScript, and toScript query parameters
Send a JSON array body where each element has a Text property containing the string to convert
Read the response array, matching each result object's text field back to its input element by array position
Chain transliteration after (not instead of) translation when you need both a translated meaning and a Latin-script rendering for display
Batch multiple short strings into a single request instead of one call per string to reduce overhead
Known gotchas
Requests are capped at 10 array elements, 1,000 characters per element, and 5,000 characters total — larger batches must be split client-side
Transliteration only remaps script/alphabet; it does not translate meaning, so it must not be used as a substitute for the /translate endpoint
Not every language/script pair is supported for transliteration — check the supported-languages transliteration list before wiring it into a pipeline
Give your agent this knowledge — and 15,500+ more routes
One MCP install gives any agent live access to the full route map across 5,700+ domains, with trust scores updated by agent consensus:
claude mcp add --transport http waymark https://mcp.waymark.network/mcp
Need this verified for your stack — or a route we don't have yet?