Jul 06, 2026: AI_
Snowflake Cortex AI_TRANSLATE now supports translation of up to 100,000 input tokens, enabling organizations to translate large documents and long-form text directly in Snowflake. Customers can now translate documents, lengthy transcripts, and conversation logs that previously exceeded the function’s context limits without manually splitting text or building custom preprocessing pipelines.
Key use cases include:
- Document translation: Translate lengthy reports, contracts, manuals, and knowledge base articles while preserving document coverage.
- Transcript translation: Translate long customer support calls, meetings, interviews, and other conversational transcripts for multilingual analysis.
- Translate complete business documents: Translate lengthy reports, contracts, technical manuals, research papers, and knowledge base articles in a single SQL query.
- Translate long customer conversations: Translate hours-long customer support calls, meeting transcripts, interviews, and contact center conversations without manually splitting transcripts.
- Localize enterprise content at scale: Translate product documentation, internal communications, operational procedures, and customer-facing content across supported languages directly in Snowflake.
- Simplify multilingual data pipelines: Translate long-form text entirely within Snowflake using SQL, eliminating custom document-splitting logic and external translation workflows.
For more information, see AI_TRANSLATE.