Translate PDF

The Translate PDF API is an AI-powered REST API Tool that uses OpenAI technology to intelligently translate the language of the text found within any PDF, Markdown, or Plain Text file. It is designed for global accessibility, accurately converting content into your specified target language while preserving context.

Yes, the Translate PDF API is categorized as a Pro Tool, which is part of a suite of advanced and specialized APIs. This tool is included with Pro and Enterprise plans. Premium plan users can also access it with a per-call fee.

The API is versatile and accepts three main file types: PDF, Markdown (.md), and Plain Text (.txt) files.

The API ensures high-quality translation through robust pre-processing. First, it converts the input document's text into a structured Markdown format, which preserves the original structure (like headings and lists). This allows the OpenAI model to receive richer, more organized input, leading to a significantly more accurate and contextually relevant translation.

The API supports translation to and from virtually any common language supported by OpenAI's advanced models. You must specify the target language using a valid IETF BCP 47 language tag (e.g., en, es-419, zh-Hant).

You use the output_language parameter, which requires a standard IETF BCP 47 language tag (ISO 639 code) and optional subtags:

• Language Code: The primary language identifier (e.g., en for English, ja for Japanese).
• Optional Script Subtag: For different writing scripts (e.g., Hant for Traditional Chinese: zh-Hant).
• Optional Region Subtag: For regional dialects (e.g., BR for Brazilian Portuguese: pt-BR, or 419 for Latin America: fr-419).

Yes, you can restrict the translation using the pages parameter. You can specify a single page number (e.g., 5) or a page range (e.g., 1-5, 10-last) for PDF documents. This parameter is ignored for Markdown and Plain Text files.

The API supports two formats for the final translated text, controlled by the output_format parameter: plaintext and markdown. Choosing markdown is recommended as it helps preserve the structure of the translated document.

You have flexible control over the output delivery using the output_type parameter:

1. json (Default): The translated text, along with the detected source languages, is included directly within the JSON response.
2. file: A secure download URL is provided, allowing you to retrieve the translated content as a separate downloadable file.

No. Your files and any data you provide are never used for AI training or shared with third parties. We partner with OpenAI through their API, and as stated in their privacy policy, they do not train models on data used through their API.

Ensuring the security and privacy of your data is a top priority at pdfRest. Our platform is built for robust, enterprise-grade security and compliance, including GDPR and HIPAA. All your files are secured with encryption during both transit and at-rest, and they are permanently deleted after the stated file retention period (30 minutes for most plans).

To facilitate GDPR compliance for your translation workflows, pdfRest processes your data within the European Union and adheres to other strict data protection requirements. You can ensure all processing occurs within the EU by sending your API calls to the dedicated EU endpoint. Please note that a GDPR usage fee may apply for some plans.

Integrating the Translate PDF API is straightforward. We offer comprehensive API documentation and code samples in many programming languages. The API Lab also allows you to test and generate code snippets directly from your browser, simplifying the setup and ensuring a smooth integration experience.

No, the Translate PDF API is not available in self-hosted versions of our product. This tool relies on calling out to the OpenAI API, and our self-hosted products only support fully self-contained processing capabilities. To use PDF Translation, you must use our Cloud API service.