Official documentation
Audio understanding (Gemini API)
Google, Google AI for Developers, 2026
Read the originalRead on October 17, 2026
- What it is
- Google's guide to sending audio to Gemini models in a prompt. It covers transcription, translation and speaker diarization, and lists the token rate and the maximum audio length per prompt.
- How much weight it carries
- Official Google documentation, read on 2026-10-17. Copies of the page on other sites show different model names, so use the live page. The page points real-time speech-to-text to a different Google product, which conflicts with the live transcription guide.
Facts taken from this source
- Google's Gemini API documentation gives the maximum audio length as 9.5 hours per prompt.
“Max length: 9.5 hours of audio per prompt” (Technical details about audio)
- Google's audio guide says Gemini models use 32 tokens for each second of audio, which is 1,920 tokens per minute.
“32 tokens per second of audio (1 minute = 1,920 tokens)” (Technical details about audio)
- Google's Gemini audio overview lists describing, summarizing and answering questions about audio as use cases, alongside transcription.
“Describe, summarize, or answer questions about audio content” (Overview)
- Google's general Gemini audio guide says that for dedicated speech-to-text models with real-time transcription, you should use the Google Cloud Speech-to-Text API.
“For dedicated speech to text models with support for real-time transcription, use the Google Cloud Speech-to-Text API” (Overview)
- Google's Gemini audio documentation lists transcription and translation of speech among the things a Gemini model can do with audio input, alongside describing, summarizing and answering questions about the audio.
“Transcription and translation (speech to text) Speaker diarization (identifying different speakers)” (Audio understanding overview, use cases)
Pages that rest on this source
- Transcribe Audio With Whisper, ChatGPT or GeminiGuide
- AI Voice Notes: From Rambling to Summaries and To-DosGuide
- Can Gemini transcribe audio?Question
- Does Gemini have a speech-to-text API?Question
- Which APIs combine speech to text and translation?Question
- Transcription: How to Turn Audio and Video Into TextTopic
- How do you translate a voice recording into English text?Question