Google says its latest Gemini transcription model can turn your ramblings into structured text

Google unveiled Gemini 3.5 Transcribe, an AI audio model that detects over 85 languages, removes filler words, and formats unstructured speech into clean text while handling self-corrections and custom vocabularies such as alphanumeric strings. It can attribute speech to up to three speakers with word-level timestamps and will be integrated into Chrome fields, Android “Rambler,” the macOS Gemini app, Google Antigravity, Search Live, Gemini Live, Docs, Keep, Gmail, and accessible via API.