An API used to quickly detect faces from an image file. Can detect up to 20 faces at a time.
Is an API used as OCR (Optical Character Recognition), to extract text in an image, supports handwriting
Detect multiple objects in an image, extract detected object names
Translate text into other languages. Can translate long texts, fast processing, cost-effective.
Convert text to audio quickly, supports over 100 languages and 300+ speakers