Use Cases

View as Markdown

genre and model_type are the two settings that change per content type. Everything else in the request stays the same across the flow described in the Overview.

The pairings below are suggested starting points, not API-defined defaults or benchmarked recommendations. The API only validates that genre is one of its six enum values and that model_type is lite or plus, and does not enforce any content-type mapping.

Content typegenre
General non-fictionNON_FICTION
Adult fictionADULT_FICTION
Children’s fictionCHILDREN_FICTION
Religious textRELIGIOUS
LegalLEGAL
AcademicACADEMIC

model_type is a separate choice: lite for faster turnaround on short-form content, plus for higher quality on long-form content. Defaults to plus.

Example

1{
2 "job_name": "document-hi",
3 "source_language_code": "en-IN",
4 "target_language_codes": ["hi-IN"],
5 "original_filename": "document.pdf",
6 "genre": "LEGAL",
7 "model_type": "plus"
8}