> ## Documentation Index
> Fetch the complete documentation index at: https://docs.urantia.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Translations

> Spanish text for all 197 papers: add lang=es on the API, the MCP server, and the SDK.

The Urantia Papers are available in Spanish: every paragraph of the Foreword and the 196 papers, and every paper, section, and part title. The Spanish is a machine translation, released as CC0 (public domain). Each translated paragraph has a label that says so.

## Get the Spanish text

Add `lang=es` to a request. Without `lang`, the API returns English, as before.

```bash theme={null}
curl "https://api.urantia.dev/paragraphs/1:0.1?lang=es"
curl "https://api.urantia.dev/papers/1?lang=es"
curl "https://api.urantia.dev/toc?lang=es"
```

These endpoints accept `lang`:

| Endpoint | What is in Spanish |
| - | - |
| `GET /toc` | Part titles, part sponsorships, and paper titles |
| `GET /papers` | Paper titles |
| `GET /papers/{id}` | The paper title, and the text and section title of each paragraph |
| `GET /papers/{id}/sections` | Section titles |
| `GET /paragraphs/{ref}` | The paragraph text and its titles |
| `GET /paragraphs/{ref}/context` | The paragraph and the paragraphs around it |
| `GET /paragraphs/random` | The paragraph text and its titles |
| `GET /entities/{id}/paragraphs` | The paragraphs that name the entity |
| `GET /search`, `POST /search` | Searches the Spanish text and returns Spanish paragraphs |
| `GET /search/semantic`, `POST /search/semantic` | Returns Spanish paragraphs for a question in Spanish or English |

With `include`, the Papers parallels (`urantiaParallels`) come with their Spanish text and titles, and the entity mentions (`entities`) with their Spanish names. The Bible and the other works in an include stay in English.

## Search in Spanish

Keyword search with `lang=es` searches the Spanish text. A word matches with or without its accents ("religion" finds "religión"), and "documento 1" is a reference, like "1:0.1". The results come as an exact phrase first, then paragraphs with every word. Spanish has no typo fixes.

```bash theme={null}
curl "https://api.urantia.dev/search?q=Ajustador%20del%20Pensamiento&lang=es"
```

```json theme={null}
{
  "data": [
    { "standardReferenceId": "0:5.9", "paperTitle": "Prólogo", "match": "exact", "language": "es" }
  ],
  "meta": { "total": 143 }
}
```

Semantic search with `lang=es` takes a question in Spanish or English and returns Spanish paragraphs. A question in Spanish scores lower than the same question in English, so `strength` and `meta.related` allow for that difference.

```bash theme={null}
curl "https://api.urantia.dev/search/semantic?q=%C2%BFQu%C3%A9%20es%20el%20alma%3F&lang=es"
```

## A translated paragraph

```json theme={null}
{
  "data": {
    "standardReferenceId": "1:0.1",
    "paperTitle": "El Padre Universal",
    "sectionTitle": null,
    "text": "EL Padre Universal es el Dios de toda la creación, la Primera Fuente y Centro de todas las cosas y de todos los seres. Piensen en Dios primero como creador, después como controlador y, por último, como sostenedor infinito. ...",
    "language": "es",
    "translation": {
      "method": "machine",
      "license": "CC0-1.0",
      "review": "auto_checked"
    }
  }
}
```

The other fields (`id`, `htmlText`, `labels`, `audio`, and the rest) are the same as in English. `htmlText` holds the Spanish text with the same markup.

| Field | Meaning |
| - | - |
| `language` | The language of `text`. A paragraph with no translation returns English and `"eng"` |
| `translation.method` | Always `machine` |
| `translation.license` | Always `CC0-1.0` |
| `translation.review` | `auto_checked`: the automatic checks found no problem. `needs_review`: a check flagged the paragraph (its length, a term, or a number), so a person should read it before you rely on it. About 1,240 paragraphs have `needs_review` |

Show the label to your readers, for example "Machine translation". Do not present the Spanish as an official or human translation.

## In the MCP server

The paper, paragraph, and search tools take `lang: "es"`: `toc.get`, `papers.list`, `papers.get`, `papers.sections`, `paragraphs.get`, `paragraphs.context`, `paragraphs.random`, `search.fulltext`, and `search.semantic`. Each Spanish paragraph has `language` and `translation`, as in the REST API. See [MCP Servers](https://docs.urantia.dev/mcp-servers.md).

## In the SDK

`@urantia/api` 0.7.0 and later for the papers and paragraphs, 0.8.0 and later for search:

```typescript theme={null}
const { data: toc } = await api.toc.get({ lang: 'es' })
const { data: paper } = await api.papers.get('1', { lang: 'es' })
const { data: p } = await api.paragraphs.get('1:0.1', { lang: 'es' })
p.translation // { method: 'machine', license: 'CC0-1.0', review: 'auto_checked' }
const { data: hits } = await api.search.fullText({ q: 'Ajustador del Pensamiento', lang: 'es' })
const { data: near } = await api.search.semantic({ q: '¿Qué es el alma?', lang: 'es' })
```

## What stays in English

* **Audio.** All narration is English.
* **Topic labels** on papers and paragraphs.
* **Some entity descriptions.** Spanish has a description for 2,517 entities; the others stay in English. See [Entities](https://docs.urantia.dev/entities.md#translated-entities).
* **The Bible and the other works.**

## How the translation was made

AI models translated the English, one paper at a time, with a glossary of the terms that the Papers use. No existing Spanish translation was a source. An automatic check compares each paragraph with published translations, and a paragraph that is too close goes back for a new translation.

The text uses "ustedes" for the plural "you", lowercase pronouns for God ("él", "su"), and « » for quotations, so that it reads well in every Spanish-speaking country.

To report a wrong word or an error, use [Feedback](https://docs.urantia.dev/feedback.md) and give the reference of the paragraph.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.