Amazon Transcribe and Polly
Learn about Amazon Transcribe and Amazon Polly to convert speech to text and text to speech.
Amazon Transcribe
Amazon Transcribe is an automatic speech recognition service that converts speech into text. It is a fully managed service that Amazon constantly trains to yield better results. The service does not require any prior machine-learning experience and can be integrated with applications without extensive setup.
How Amazon Transcribe works
Amazon Transcribe uses deep-learning technologies to transcribe live or pre-recorded audio files. In addition to the transcribed text, it provides additional metadata about the content, such as confidence scores, timestamps for words, and punctuation marks.
Amazon Transcribe divides its transcription methods into two categories:
Streaming transcription: The real-time transcription of audio lies in the Streaming transcription category. It enables the transcription of live audio streams as they occur. Streaming media, including live news broadcasts, speeches, pre-recorded podcasts, movies, and others, are delivered to Amazon Transcribe in real-time, and the transcribed results are received simultaneously.
Amazon Transcribe also offers the capability to ...