# Translate HTML, Markdown or tagged text and keep the markup

> Translate HTML, Markdown or tagged text and keep the markup: 0 companies fully do it, 10 with a limit, 17 carry the tag. Every listing in Translation with the reason and a source.

- Canonical: https://www.anchorterminal.com/niches/translation.translate-markup/
- Markdown: https://www.anchorterminal.com/niches/translation.translate-markup/index.md (~1,250 tokens)
- Slim: https://www.anchorterminal.com/niches/translation.translate-markup/index.min.md (~380 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/niches/translation.translate-markup/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-15

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |
| --- | --- | --- | --- | --- |
| 0 | 10 | 17 | 10 | 6 |

## What counts as done

Output with the same tags, attributes, comments and Markdown structure, spaces around tags kept, only human text translated, and formatting options honoured whether or not the source language is given.

How agents ask for it: translate this web page HTML; translate the Markdown docs; translate this string with tags in it; translate the email template

## Does the job, with a limit

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

- **Amazon Translate (Amazon Web Services, Inc.)**: HTML is translated in real-time documents and batch jobs, with do-not-translate tags, but Markdown is not a supported format.
- **Azure Translator (Microsoft Corporation)**: HTML text type is supported, but a first-hand report translating Markdown lost bold, changed asset paths and broke front matter.
- **Crowdin (Crowdin OÜ)**: HTML and Markdown documentation formats are handled as source files through the project workflow, but tag and front-matter preservation was not documented on the pages read.
- **DeepL API (DeepL SE)**: tag_handling html or xml keeps markup and Markdown is a document format, but open reports show comments causing parse errors, spaces before tags dropped, table numbers dropped, and preserveFormatting ignored under auto-detect.
- **Google Cloud Translation (Google LLC)**: HTML is translated with mimeType text/html, but Markdown is not a supported type, so its structure is not preserved.
- **Lara Translate API (Translated s.r.l.)**: content_type text/html and application/xliff+xml are accepted on text calls, with XLIFF limited to a set of inline tags, and Markdown is a document format; tag-spacing behaviour is not documented.
- **LibreTranslate (LibreTranslate)**: format=html translates HTML markup, but Markdown is not a format option.
- **Lingvanex Translation API (Nordicwise Limited)**: translateMode html translates HTML strings, but Markdown is not offered and tag-handling behaviour is not documented beyond the example.
- **SYSTRAN Translate API (SYSTRAN SAS)**: A format parameter selects the source format from the supported list, but tag and Markdown preservation are not described on the reference.
- **TranslatePlus (PetaBytes, Inc.)**: /v2/translate/html and /v2/translate/email take up to 200,000 characters and return HTML with tags preserved, but Markdown has no endpoint and tag-spacing behaviour is not described.

## Couldn't check

The docs were closed to us, or silent. These carry no mark either way.

- **Lingo.dev (Replexica, Inc.)**: The Localize page documents key-value data only and says nothing about HTML or Markdown inside values; no markup handling page was read.
- **Localazy (Localazy s.r.o.)**: No HTML or Markdown handling was documented on the AI Translation page read.
- **Lokalise (Lokalise, Inc.)**: HTML or Markdown handling inside keys or documents was not documented on the pages read.
- **Phrase (Phrase a.s.)**: Supported file formats for markup and tag handling on text calls were not documented in the Language AI spec read.
- **Smartcat (Smartcat Platform Inc.)**: HTML and Markdown handling was not documented on the guides read.

- not this job: POEditor MCP server (Code Whale Inc.): No markup translation tool; HTML or Markdown would have to be split into terms first.

## What stops agents finishing

- markup with comments or nesting rejected
- Markdown not supported as a format, so structure is lost
- option silently dropped under auto-detect

## Around it

Before: cms.read-page, web-scrapers.page-to-markdown. After: cms.update-page, email.send.

## Where this comes from

Weight 10 of 100 in Translation: 6 of 55 accounts (HTML comments, spaces around tags, Markdown and front matter, options ignored with auto-detect)

As data: https://www.anchorterminal.com/api/v1/use-cases/translation.translate-markup.json, or the MCP tool get_use_case with id translation.translate-markup. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
