Official documentation
Speech-to-Text overview (Google Cloud)
Google Cloud, 2026
Read the originalRead on October 17, 2026
- What it is
- Google Cloud's overview of its Speech-to-Text API, which describes synchronous, asynchronous and streaming recognition and their audio limits.
- How much weight it carries
- Google's own documentation, read on 2026-10-17. Limits in the documentation can change, so check the current page before you build.
Facts taken from this source
- Google's Speech-to-Text overview says each alternative in the response contains the recognized text as a transcript. The overview does not describe translation.
“Each alternative in the response contains a transcript with the recognized text.” (Help page text)
- Google says synchronous recognition requests process audio of 1 minute or less.
“Synchronous recognition requests process audio data of 1 minute or less.” (Recognition methods)