Posted On: Nov 24, 2020
Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for you to add speech-to-text capabilities to your applications. Today, we are excited to announce native support for Ogg opus and FLAC encoded audio in Amazon Transcribe for streaming transcription. Previously, you were required to transcode audio streams with these encodings to PCM encoding which added extra costs and scaling challenges for large workloads.
Ogg opus refers to opus encoded audio frames in an Ogg container and is often the preferred audio compression technology for real-time, interactive communications due to its high fidelity and low-latency. FLAC is a lossless audio codec that creates a bit-perfect reproduction of your original audio, while still being compact to transmit. Starting today, live audio applications that use Ogg opus and FLAC encoding such as in-game chat can use the Amazon Transcribe streaming API to automatically generate captions. You can also use the streaming API to efficiently and accurately generate transcripts for diverse use cases, such as transcribing contact center calls, subtitling live broadcasts and capturing meeting notes for business productivity.