Skip to main content

Language Support

Learn about ToltIQ's multi-language document processing capabilities. This guide covers supported languages, document format requirements, and how to work with documents in Roman character languages and other non-Roman character languages.

Written by Christa Jagnanan
Updated over 6 months ago

What languages does ToltIQ support?

ToltIQ supports documents in multiple languages, with different capabilities depending on the character system used:
​Roman Character Languages (Full Support): Languages that use the Latin/Roman alphabet are fully supported across all document types, including:
​

  • English

  • Spanish

  • French

  • German

  • Italian

  • Portuguese

  • And other European languages using Roman characters

Non-Roman Character Languages: Languages using non-Roman characters have varying levels of support:
​

Full Support (All Document Types):
​

  • Japanese

  • Chinese (Simplified and Traditional)

  • Korean

PDF-Only Support:
​

  • Arabic

  • Hebrew

  • Russian

  • Thai

  • And other languages using non-Roman character systems

What document types work with non-Roman character languages?

For Roman character languages: All document types are supported (PDF, Word, Excel, PowerPoint, etc.)
​For Chinese, Japanese, and Korean: All document types are supported (PDF, Word, Excel, PowerPoint, etc.)
​For other non-Roman character languages: Currently, only PDF format is fully supported for optimal processing and analysis.
​If you need to analyze non-Roman character documents:
​For Chinese, Japanese, or Korean documents:
​

  • Upload in any supported document format (PDF, Word, Excel, PowerPoint, etc.)

  • No special conversion required

  • Ensure documents contain readable text (not just scanned images)

For other non-Roman character languages:
​

  1. Convert your documents to PDF format before uploading

  2. Ensure the PDF contains searchable text (not just scanned images)

  3. Upload to ToltIQ as you would any other document

Why are some non-Roman character languages limited to PDFs?

PDF format provides the most reliable text extraction and processing for certain complex character systems. This ensures:
​

  • Accurate character recognition

  • Proper text extraction for AI analysis

  • Consistent formatting preservation

  • Reliable citation and footnoting

However, Chinese, Japanese, and Korean now have full support across all document types due to improved translation and processing capabilities.
ToltIQ continues to improve language support and may expand additional languages to more document types in the future.

Enabling Language Support

Do I need to enable specific languages before using them?

For Roman character languages: No configuration needed—these languages work automatically across all document types.
​For Chinese, Japanese, and Korean: No configuration needed—these languages work automatically across all document types.
​For other non-Roman character languages: Some languages may require enablement by the ToltIQ support team to ensure optimal processing.

If you need to process documents in non-Roman character languages other than Chinese, Japanese, or Korean (which are already supported for all document types):
​Step 1: Prepare your request
​

  • Identify which language(s) you need enabled

  • Note the document types you'll be working with

  • Estimate the volume of documents you'll be processing

Step 2: Contact ToltIQ Support
​

  • Reach out to the ToltIQ support team - support@toltiq.com

  • Specify the language(s) you need

  • Mention your Deal or project context

Step 3: Confirmation
​

  • The support team will enable the language(s) for your account

  • You'll receive confirmation when processing is ready

  • You can then upload and analyze documents in that language

Note: Chinese, Japanese, and Korean are already supported for all document types and do not require special enablement.
You can then upload and analyze documents in that language

Did this answer your question?