Official documentation
Speech-to-Text supported languages
Google Cloud, Google Cloud documentation, 2026
Read the originalRead on October 17, 2026
- What it is
- Google Cloud's table of the languages and regional variants its Speech-to-Text service supports, listed by model (chirp, chirp_2, chirp_3 and others) with the features each model offers for each language.
- How much weight it carries
- Official and maintained by Google, but the table changes as models are added. It lists what the API accepts, not how accurate each language is, so check accuracy on your own recordings.
Facts taken from this source
- Google Cloud Speech-to-Text lists Arabic (Egypt) with the code ar-EG for its chirp_3 model.
“Arabic (Egypt) ar-EG chirp_3” (Supported languages table, Arabic (Egypt) rows)
- Google Cloud's Speech-to-Text supported-languages table lists Hindi (India), code hi-IN, for its chirp_2 model.
“Hindi (India) hi-IN chirp_2 Automatic punctuation Model adaptation Word-level confidence Profanity filter” (Supported languages table, chirp_2 column)
- Google Cloud's Speech-to-Text supported-languages table lists Japanese (Japan), code ja-JP, for its chirp_2 model.
“Japanese (Japan) ja-JP chirp_2 Automatic punctuation Model adaptation Word-level confidence Profanity filter” (Supported languages table, chirp_2 column)
- Google Cloud's Speech-to-Text supported-languages table lists Korean (South Korea), code ko-KR, for its chirp_2 model.
“Korean (South Korea) ko-KR chirp_2 Automatic punctuation Model adaptation Word-level confidence Profanity filter” (Supported languages table, chirp_2 column)
- Google Cloud's Speech-to-Text supported-languages table lists Xhosa (South Africa), code xh-ZA, for its chirp_2 model.
“Xhosa (South Africa) xh-ZA chirp_2 Automatic punctuation Model adaptation Word-level confidence Profanity filter” (Supported languages table, chirp_2 column)
- Google Cloud's Speech-to-Text supported-languages table lists Zulu (South Africa), code zu-ZA, for its chirp_2 model.
“Zulu (South Africa) zu-ZA chirp_2 Automatic punctuation Model adaptation Word-level confidence Profanity filter” (Supported languages table, chirp_2 column)
- 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.
“Use only the language codes shown in the following table” (Introduction to the supported languages table)
Pages that rest on this source
- What is the best Arabic speech to text API?Question
- Hindi Voice Typing and Speech to TextGuide
- Which speech to text API works best for Indian languages?Question
- Japanese, Chinese and Korean Speech to TextGuide
- How do you transcribe Japanese, Chinese or Korean audio?Question
- How do you translate Japanese audio to English?Question
- Can AI transcribe Zulu, Xhosa and other African languages?Question
- Can you translate Zulu or Xhosa audio to English?Question
- How many languages does Google Speech-to-Text support?Question