Google Launches Gemini 3.5 Transcribe, Its Most Precise Speech-to-Text Model Yet
Google introduced Gemini 3.5 Transcribe on August 26, 2026, describing it as its "most precise speech-to-text model yet" and a completely new addition to the Gemini family. The model converts raw audio directly into formatted, polished text and supports more than 85 languages, with specialized jargon detection and a customizable vocabulary that adapts to unique spelling requirements. Google said the model represents a major advancement over Chirp 3, its previous transcription model, particularly in multilingual performance and word error rates. Google AI Blog
Beyond straight transcription, Gemini 3.5 Transcribe lets users edit text naturally with their voice. It can automatically format output and remove filler words such as "um" and "uh." For multi-speaker scenarios, the model attributes speech for up to three speakers in pre-recorded audio and provides word-level timestamps. It is already powering several of Google's first-party products. 9to5Google
Alongside Transcribe, Google updated the broader Gemini Audio lineup with two live models: Gemini 3.5 Live and Gemini 3.5 Live Experimental. Both build on the speech recognition technology that powers Gemini's voice chat mode. Gemini 3.5 Live improves handling of mid-sentence interruptions, automatic language recognition, and live visual processing. Gemini 3.5 Live Experimental takes a different approach to complex tasks: it narrates its reasoning step by step in real time, giving users visibility into the model's intermediate processing before it produces a final answer. The Verge
The rollout is staged. The Gemini Audio updates are available now in English for all macOS Gemini app users. On Android, the Rambler dictation feature is live in select countries and languages. Chrome support is coming soon, and Google said Gemini 3.5 Transcribe will eventually let users apply speech-to-text in any web field within the browser. For developers, all three new models are available in public preview through the Gemini API via AI Studio and Antigravity. Engadget
The broader context here is that Google has been steadily building an audio model stack across both its proprietary Gemini line and its open Gemma family. Gemini 3.5 Live Translate, announced in June 2026, delivers near real-time speech-to-speech translation across more than 70 languages. On the open-source side, Gemma 3n introduced an advanced audio encoder for on-device speech-to-text on clips up to 30 seconds, and the more recent Gemma 4 12B is designed to bring agentic, multimodal intelligence to the laptop, including fully local transcription. Gemini 3.5 Transcribe sits at the top of that stack as the cloud-side, full-featured model.
What distinguishes Gemini 3.5 Transcribe from conventional automatic speech recognition is not just accuracy but the post-processing layer. Automatic filler-word removal, voice-driven editing, and formatting happen inside the model pipeline rather than requiring a separate NLP pass or user-scripted cleanup. For developers building transcription into applications, that consolidation reduces integration complexity. The customizable vocabulary feature matters for domains where generic ASR consistently fails: medical terminology, legal Latin, product code names, and other specialized lexicons that force downstream correction workflows.
The speaker attribution and word-level timestamp capabilities position the model for use cases beyond dictation. Pre-recorded audio with up to three speakers covers a meaningful slice of meeting, interview, and podcast transcription scenarios, though it stops short of the multi-speaker diarization that enterprise call-center and media-production workloads often require.
Worth flagging is the gap between the current feature set and what Google has said is coming. Speech-to-text in any Chrome web field would put Gemini 3.5 Transcribe directly in the browser's input layer, a move that would extend the model's reach from app-embedded use to the broader web. Google has not provided a date for that capability or for broader Chrome support. The staged rollout, currently English-only and macOS-first on the consumer side, suggests Google is validating the model's real-world performance before widening access.
For developers evaluating the API, the public preview in AI Studio and Antigravity is the practical entry point. The model is already production-deployed in Google's own products, which provides some signal about its readiness, though first-party usage conditions and third-party API performance can diverge in areas like latency under load and rate limits.
