Google has updated Gemini Audio with some new Gemini 3.5 models, introducing new transcription capabilities that automatically detect specialized jargon and more than 85 languages. Gemini 3.5 Live, 3.5 Live Experimental, and 3.5 Transcribe are designed to provide better precision for Google\u2019s voice-controlled AI features, without struggling with background noise or when your speech is interrupted.<\/p>\n
Gemini 3.5 Transcribe is a completely new addition to the Gemini family, and its introduction comes as we\u2019re still waiting for Google to release the Gemini 3.5 Pro<\/a> model that it promised to roll out in June<\/a>. Google says that 3.5 Transcribe \u201crepresents a major advancement from our previous transcription model, Chirp 3,\u201d especially regarding multilingual performance and wording error rates.<\/p>\n The transcription model allows users to \u201cedit naturally with just your voice,\u201d according to Google, and can automatically format text and remove filler words like \u201cum\u201d and \u201cuh.\u201d Users can provide a customized vocabulary to the model, allowing 3.5 Transcribe to automatically adapt transcription to unique spelling requirements and specialized jargon to prevent those words from being edited manually. It can also attribute speech for up to three speakers in pre-recorded audio, alongside providing word-level timestamps.<\/p>\n