Translate Multiple Files (currently supports document, video)

HTTP request

POST /v3/process

Authorization

OAuth2PasswordBearer

Authorization: OAuth2PasswordBearer

Request Body schema: json data

KEY	TYPE	VALUE
task_type	String	Classifying tasks corresponding to each translation mode such as: document, images, audio, video, summarization, create_video
original_lang	String	The original language of the content. Optional but recommended for better accuracy.
dest_lang	String	The target language for translation.
process_mode	String	Describes how the file should be processed 'replace', 'append', 'append_reverse' .
translate_type	String	Specifies the translation engine or version to be used. Paraphrase, Professional
meta_files	String	The value is taken from the upload api Example: [ { "filename": "2.text_image.pdf", "status": true, "credits": 4.92, "task_id": "f911298671b240f5984060c62cbbb218", "size": "0.18 MB" }, { "filename": "5.text_images.docx", "status": true, "credits": 2.89, "task_id": "af60061f95c8439a9ee55971b37a7e06", "size": "0.3 MB" } ]
is_translate_images	Bool	Flag indicating whether images within the document should also be translated.
tone	String	Tone of the translation, if applicable
domain_translate_document	String	The domain or field of the content for document, which can help in choosing specialized translation models.
domain_translate_image	String	The domain or field of the content for image, which can help in choosing specialized translation models.
domain_translate_audio	String	The domain or field of the content for audio, which can help in choosing specialized translation models.
domain_translate_video	String	The domain or field of the content video, which can help in choosing specialized translation models.
bilingual_text_style__font	String	Used to set the font for the bilingual translation mode and when process_mode=append
bilingual_text_style__color	String	Used to set the color for the bilingual translation mode and when process_mode=append
dictionary	List	Optional custom dictionary in JSON format to be used for the translation, specifying word-level translations. Example: [ { "ori_lang": "en", "des_lang": "vi" "ori_word": "hello", "des_word": "xin chào", }, { "ori_lang": "en", "des_lang": "vi" "ori_word": "hi", "des_word": "chào", }]
custom_prompt	String	Custom prompt to be used for the translation
output_format	String	1. Scanned PDFs These are image-based PDFs, typically from printed or photographed documents. auto: Automatically selects the best format for readability. The translated text will follow the original content as closely as possible, but layout may vary. docx: Text is extracted and translated with a focus on preserving the original wording. Layout and formatting may not be retained. pptx: Not recommended unless the scanned file has a visual structure that benefits from slide-based formatting. 2. Regular PDFs These contain selectable digital text and may include structured layouts or design elements. auto: Automatically chooses between DOCX and PPTX to best preserve the original layout and formatting. docx: Suitable for text-based documents. May simplify layout while keeping the content intact. pptx: Best for visually rich documents (e.g., presentations, flyers). Maintains layout, formatting, and visual fidelity.

Response

200: Success

Response schema: application/json

KEY	VALUE
status_code	200
content	{ "data": { "task_id": "0d05c89e6f2c472ab86b291516e8e466" }, "errors": [], "error_description": "", "start_time": "2024-03-11 13:05:42.080757", "end_time": "2024-03-11 13:05:42.348086", "status": "success" }

400: Bad Request

KEY	VALUE
status_code	400
content	{ "data": {}, "errors": [ "Error" ], "error_description": "Error while sending message. Please check server!", "start_time": "yyyy-mm-dd hh-mm-ss utc+7", "end_time": "yyyy-mm-dd hh-mm-ss utc+7" }

401: Authentication Error

KEY	VALUE
status_code	401
content	{ "detail": "Not authenticated" }

Response schema: application/json

detail