Vision API
- Vision detection
- Labelling
- Face / landmark recognition
- OCR
- Explicit content tagging
Video API
- Annotate videos
- From GCS, live streams or local videos
- Contextual info
- From single frame to entire video
- Recognise text
- Track objects
- Recognise people
Translation API
- 100+ language translation pairs
- Language detection
- Basic or advanced versions
- Advanced—batch requests, Auto ML custom models
Text-to-Speech and Speech-to-Text APIs
- Fast text-to-speech and vice versa
Natural Language API
- Text analysis—insights from documents (e.g. emails, social media)
- Sentiment analysis