Convert speech to text Stay organized with collections Save and categorize content based on your preferences.
This page shows you how to use Vertex AI Studio to convert speech to text.
To learn how to convert text to speech, seeConvert text to speech.
Convert speech to text
To convert speech to text, do the following:
In the Vertex AI section of the Google Cloud console, go totheVertex AI Studio page.
ClickGenerate speech.
Select theSpeech-to-text tab.
InSpeech, clickBrowse to select the audio file that you want toconvert to text.
In theLanguage selector box, select the language of the speech in theaudio file.
ClickSubmit.
The converted text appears inText.
Limitations
- Audio files can be a maximum 60 seconds or 10 MB (whichever is less).
- Files are transcribed with theChirp model.
- Only 16-bit linear PCM WAV files are supported.
You can use theSpeech-to-Text UI directly to overcome these limitations.
What's next
- For more models, advanced features, and ability to transcribe files up to 8 hours, seeSpeech-to-Text.
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2026-02-19 UTC.