GoKawiilGoogle launches Gemini Audio models to power live dialogue and transcription
Google has released Gemini Audio, a set of three new speech-focused AI models: Gemini 3.5 Live, 3.5 Live Experimental, and 3.5 Transcribe. These models are meant to handle real-time conversation and speech-to-text tasks and are rolling out across Search Live, Gemini Live, Docs, Keep, Gmail, the Gemini app, and Gboard. Notably, Gemini 3.5 Transcribe replaces Google's older Chirp 3 model and adds features like filler-word removal, auto-formatting, and voice editing.
GoKawiil's interpretation of the reporting above, not reported fact.
Even as Google pushes forward with newer Gemini 3.6 and 3.7 releases, it's still investing in the 3.5 line specifically for voice tasks, showing that speech recognition and live conversation remain a distinct priority separate from general model upgrades. Better transcription with wide language support and function-calling ability could make Google's productivity apps more useful for hands-free work and multilingual users. It also signals Google's intent to compete more aggressively with voice-first AI assistants.
- Gemini Audio includes three models: 3.5 Live, 3.5 Live Experimental, and 3.5 Transcribe
- 3.5 Transcribe replaces Chirp 3 and supports over 85 languages with better context awareness
- The models are rolling out across Search Live, Gemini Live, Docs, Keep, Gmail, Gemini app, and Gboard
Google Pixel Buds Pro 2 — If Gemini Live's new real-time conversation models sound appealing, Pixel Buds Pro 2 are built to tap Gemini hands-free straight from your ears. They pair tightly with Android and let you talk to Gemini without pulling out your phone, making the new Gemini Audio dialogue models feel genuinely conversational.
See Google Pixel Buds Pro 2 on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: androidauthority.com, 2026-08-26
Published there as: “Google rolls out Gemini Audio to improve real-time dialogue and speech recognition”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.