Google Speech-to-Text

Google Speech-to-Text converts audio into accurate text using neural network models for 125+ languages and variants.

Deploy the Chirp model within Google Speech-to-Text to transcribe audio across 125+ languages. This API automates complex tasks: it identifies distinct speakers (diarization), filters background noise, and applies automatic punctuation in real time (streaming or batch). Power your voice commands in apps or generate captions for global media. Integrate it with Google Cloud Storage for efficient batch processing or handle live streams for immediate feedback.

https://cloud.google.com/speech-to-text