Google Translate is a multilingual neural machine translation service developed by Google. It uses an artificial neural network to increase fluency and accuracy in translating text, documents, and websites from one language into another. The neural network consists of two main blocks, an encoder and a decoder, both of LSTM architecture with 8 1024-wide layers each. Google Translate uses the bidirectional RNN to align the input and output. Firstly, it encodes the input sentence into vectors by one RNN for the input language, which is used for encoding. Then, the vectors try to be mapped by many vectors which represent words in the language of output, actually, words here are still vectors to find which one is the best match for the input sentence. Google Translate supports 133 languages at various levels as of 2022.