Speech-to-Text RPC API reference

This is the gRPC API reference for Speech-to-Text. It is one of the Vertex AI pre-trained APIs available on Google Distributed Cloud Hosted (GDCH).

Use this guide to programmatically integrate speech recognition technologies into developer applications. Send audio and receive a text transcription from the Vertex AI Speech-to-Text API service. For example, if you submit audio in Spanish, a corresponding text transcription in Spanish is the result.

Speech-to-Text methods

There are two methods available in GDCH:

  • Recognize: Performs synchronous speech recognition. Recognize receives results after all audio has been sent and processed.
  • StreamingRecognize: Performs bidirectional streaming speech recognition. StreamingRecognize receives results while sending audio.