Skip to content

Fact · Languages and accents

Google's Speech-to-Text supported-languages page says developers should use only the language codes shown in its table, and that the codes are listed for each model and region.

Checked against its source on October 17, 2026

In the source's own words

“Use only the language codes shown in the following table”

Speech-to-Text supported languages, Google Cloud, Google Cloud documentation, 2026, Introduction to the supported languages table.

Open the original
What it measures
The table gives each language as a code with a region or variant, such as Arabic (Egypt) with the code ar-EG, and marks which models support each one. A single language often appears under several codes, so a count of rows is not a count of languages.
What it does not show
The page is a working reference that changes as models are added. Counting its rows gives variants, not a number of languages, so the headline figure on the product page is the one to quote.

Source

Cited on

Google Speech-to-Text: use only the codes in its table | Yap