Speech-to-Text UI Overview

The Cloud Speech-to-Text console allows you to transcribe audio files using Google's AI technologies. You can refine your transcription results until you achieve your desired outcome, then use that transcription configuration to transcribe audio using the Speech-to-Text API.

Speech-to-text console main features

Create transcription - Choose audio files and set configuration options.

Screenshot of the Create a Audio Transcription page in the console.

Transcriptions - Find previous transcriptions

Screenshot of the Transcription List page in the console.

Review transcriptions by comparing generated text to the original audio. You can create new transcriptions from existing examples, making it quick and easy to subtly refine your results.

Screenshot of the Transcription Details page in the console.

Model adaptations - Boost transcription accuracy by customizing recognition of domain-specific terms and rare words and phrases.

Screenshot of the Model Adaptation page in the console.

Guides

  • Quickstart: Use the console to generate a Speech-To-Text transcription.

Reference

Resources