Speech-to-Text sample applications.
Learn how to generate captions from a video file.
Transcribe phone audio with enhanced models
Learn how to generate captions from audio captured on a phone, using an enhanced speech recognition models.
Transcribe audio from an endless stream
Learn how to transcribe audio from an infinite stream.
Implement real-time transcription in production
Deploy an example app that performs real-time transcription of an audio stream using Speech-to-Text, Google Kubernetes Engine, and Memorystore.
Optimize audio files
Shows you how to perform a preflight check on audio files that you're preparing for use with Speech-to-Text.
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.