Google Cloud Speech-to-Text

Google Cloud Speech-to-Text converts live streams and recorded audio into text through REST and gRPC APIs. Its standard, enhanced, medical, and Chirp recognition models support synchronous, asynchronous batch, and streaming workflows across a broad range of languages and audio types. Developers can use automatic punctuation, speaker diarization, word timestamps, language detection, model adaptation, custom classes and phrase sets, data residency, audit logging, and customer-managed encryption for transcription, captions, call analytics, voice interfaces, and regulated workloads.