Speech-to-Text API documentation question

52 Views Asked by At

I am taking a look at the Speech-to-Text API and I had some questions:

  1. What is the difference between v1 and v1p1?

  2. Does the chirp model in Speech-to-Text v2 support transcribing audio from a streaming input?

1

There are 1 best solutions below

0
Poala Astrid On BEST ANSWER

The versioning denotes different releases or updates to the API, with newer versions often introducing improvements, bug fixes, or new features. This information is generally available in release notes.

Streaming recognition with the 5 minute limit and transcription of MP3 encoded audio data are available in v1p1beta1 API version.

The Chirp model is not available in Speech-to-Text v2 Speech.StreamingRecognize API method.