Google Introduces Gemini 3.5 Transcribe Speech-to-Text Model

Google Introduces Gemini 3.5 Transcribe Speech-to-Text Model Google has announced Gemini 3.5 Transcribe, a speech-to-text model designed for real-time and pre-recorded audio transcription with context-aware text formatting, multi-speaker recognition, and multilingual support across Google products and developer APIs. Gemini 3.5 Transcribe provides real-time streaming via the Live API (gemini-3.5-transcribe-live) and pre-recorded audio processing via the Interactions API (gemini-3.5-transcribe). According to Artificial Analysis measurements, the model achieves average Word Error Rates of 4.0% for streaming and 2.6% for non-streaming, improving time to final transcription by 70% compared to Chirp 3. The model automatically handles disfluency cleanup, self-corrections, over 85 languages, custom vocabulary, and speaker attribution for up to three speakers. Availability includes public preview in the Gemini API via Google AI Studio and Gemini Enterprise Agent Platform, as well as integrations in Gboard on Android, macOS, and coming soon to Chrome. Model Capabilities and Benchmarks Gemini 3.5 Transcribe converts raw audio into formatted text by removing filler words like 'ums' and 'ahs' and handling real-time self-corrections. It supports more than 85 languages, custom vocabulary inputs, and speaker identification with timestamps for up to three speakers (with 3+ in experimental support). Measured by Artificial Analysis, the model delivered a 4.0% WER in streaming and 2.6% in non-streaming, alongside a 70% improvement in time to final transcription over Chirp 3. On the multilingual FLEURS benchmark, it achieved a 5.50% streaming WER and a 5.04% non-streaming WER. Developer APIs and Integration The model is offered through two primary API pathways: continuous bidirectional streaming via the Live API using gemini-3.5-transcribe-live, and pre-recorded batch audio handling through the Interactions API using gemini-3.5-transcribe. Developer frameworks such as Agora, Fishjam, LangChain, LiveKit, Pipecat, Vercel, and Vision Agents are integrating with the Live API to manage streaming media infrastructure for interactive voice interfaces. Product Implementations and Availability Gemini 3.5 Transcribe powers the Rambler voice dictation and editing feature on Gboard for Android and functions in Google Antigravity to parse screen context and chat history. In the macOS Gemini app, it enables voice commands and function calling to delegate tasks like image generation and file analysis to other Gemini models. The model is currently available in public preview through the Gemini API in Google AI Studio, Google Antigravity, and the Gemini Enterprise Agent Platform, with web dictation planned for Chrome.

Google 推出 Gemini 3.5 Transcribe 智能语音转文字模型 Google 发布了语音转文本模型 Gemini 3.5 Transcribe，旨在提供高精度的实时转录与智能语音交互体验。该模型支持处理背景噪音与不流畅发音，可直接将语音转化为排版规整的文本，并通过双版本 API 及 Google 各生态产品面向开发者和用户开放。 Gemini 3.5 Transcribe 提供 gemini-3.5-transcribe-live（实时流式，具亚秒级延迟）和 gemini-3.5-transcribe（录音处理，含说话人分配与时间戳）两套 API。 根据 Artificial Analysis 评测，流式平均词错误率（WER）为 4.0%，非流式为 2.6%，最终转录生成时间较前代 Chirp 3 缩短 70%。 模型支持 85 种以上语言自动识别，具备口误自动修正、过滤语气助词、自定义词汇识别及多说话人识别等功能。 该功能已在 Google AI Studio、Gemini macOS 应用以及 Android 版 Gboard（Rambler）等平台上线，未来还将集成至 Chrome 浏览器。 API 模式与核心智能转录能力 Gemini 3.5 Transcribe 通过 Live API 提供用于交互式语音应用的低延迟双向流式传输接口，同时通过 Interactions API 支持会议录音、通话记录等音频的离线转录，可为最多 3 位说话人提供时间戳和发言归属。模型支持自动识别并修正发音口误、消除填充词，并能结合用户自定义专有名词进行准确识别。在 macOS 应用中，它还能通过函数调用委托其他 Gemini 模型执行生图与文件解析等复杂任务。 性能指标与跨产品集成应用 相较于上一代 Chirp 3 模型，Gemini 3.5 Transcribe 在 FLEURS 基准上于流式和非流式场景分别取得 5.50% 与 5.04% 的 WER。该技术已被深度整合进 Android Gboard 的 Rambler 特性、Google Antigravity 与 Google AI Studio 中，并已在 macOS 版 Gemini 应用中上线，未来将登陆 Chrome 浏览器以支持网页端全局语音输入。目前该模型已在 Google AI Studio 和 Gemini Enterprise Agent Platform 进入公开预览阶段。

Aug 26, 2026 | Our latest speech-to-text model designed for precise and intelligent real-time transcription. Diego Melendo Casado Senior Director, Engineering, Gemini Audio Luke Leonhard Chief of Staff, Gemini Audio, on behalf of Gemini Audio Team Your browser does not support the audio element. Listen to article [[duration]] minutes This content is generated by Google AI. Generative AI is experimental Today, we’re introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions. Unlike conventional speech recognition models that struggle with background noise, complex jargon, and disfluency cleanup, Gemini 3.5 Transcribe converts raw audio directly into accurate, polished, formatted text. Across our products like the Gemini app and on Android, we’ve seen consumers already benefiting from this transcription model with new voice capabilities like Rambler on Android and in the Gemini app on macOS. Now, developers can build similar capabilities with Gemini 3.5 Transcribe in the Gemini API in Google AI Studio and Gemini Enterprise Agent Platform . We've built 3.5 Transcribe to plug seamlessly into your developer workflows, whether you’re building voice agents, real-time captioning tools, or post-call analytics pipelines. The model is available across two separate APIs: Real-time streaming: Delivers continuous, bidirectional streaming with sub-second latency for interactive voice apps via the Live API using gemini-3.5-transcribe-live . Pre-recorded audio processing: Transcribes recorded audio, meetings, call logs, and more with speaker attribution and word-level timestamps via the Interactions API using gemini-3.5-transcribe . Get more precise and intelligent transcription Gemini 3.5 Transcribe is designed to capture your natural speaking style to better understand your intent and recognize custom vocabulary, so you can execute tasks with your voice. Smart transcription: Seamlessly handles self-corrections (like "let’s meet Tuesday—no, Wednesday" ), removes filler words (“ums” and ‘“ahs"), auto-formats your text. Function calling: The model can delegate complex tasks (such as image generation and file analysis) to other Gemini models via function calls. Currently available in the Gemini macOS app . More precise transcription: As measured by Artificial Analysis, achieves an average Word Error Rate (WER) of 4.0% for streaming and 2.6% for non-streaming use-cases. It shows strong performance across noisy, real-world environments, accurately capturing alphanumeric entities like postal codes and order IDs. Custom vocabulary: Recognizes specialized jargon and unique spellings by seamlessly adapting transcriptions to your provided custom vocabulary. Global language support: Automatically detects and transcribes over 85 languages, seamlessly handling regional accents and diverse dialects. Multi-speaker identification: Accurately attributes speech in pre-recorded audio with timestamps for up to three speakers (support for 3+ speakers is experimental). Gemini 3.5 Transcribe’s performance represents a major advancement from our previous transcription model, Chirp 3, offering new capabilities, improved word error rates, and significantly better latency. As measured by Artificial Analysis, time to final transcription, for example, improves by 70%. On the FLEURS benchmark across a set of top languages and locales, the model delivers precise multilingual performance, improving over Chirp 3, and achieving a 5.50% WER in streaming mode and 5.04% WER in non-streaming use-cases. Experience smart transcription and advanced dictation In addition to the Gemini API in the Google AI Studio and Gemini Enterprise Agent Platform, 3.5 Transcribe goes further than standard speech-to-text to make working across Google feel more natural and intuitive. By bringing context-aware understanding directly into everyday surfaces like Gboard, Antigravity, the Gemini app, and Chrome, it captures nuances, intent, and inline edits with ease. On Gboard on Android, through the new Rambler feature, 3.5 Transcribe transforms spoken thoughts into well-formatted text, filtering out filler words. You can also use your voice to make edits, correct misspellings, and change the writing style. On Google Antigravity, 3.5 Transcribe pairs screen context and chat history, with your permission, to ensure pinpoint transcription accuracy across file names, agent thoughts, and active documents. In Google AI Studio , you can access 3.5 Transcribe in Build mode to vibe code apps with your voice on the fly. In the Gemini app on macOS , 3.5 Transcribe not only transcribes your free natural speech into clean formatted text, but also enables voice commands that can pair seamlessly with screen context to power complex workflows. By calling on other Gemini models in the background to handle the heavy lifting, the model makes it effortless to summarize local files, repurpose text across apps, or generate images right at your cursor—using just your voice. Coming soon to Chrome , you’ll be able to talk to type in any web field — making it effortless to dictate replies, draft posts, or prompt Gemini in Chrome more naturally and easily with your voice. Read the early reviews By leveraging the Gemini Live API, developer platforms such as Agora , Fishjam , LangChain , LiveKit , Pipecat , Vercel , and Vision Agents enable developers to build and deploy high-performance voice-driven interfaces with ease. These platforms manage complex real-time media streaming infrastructure behind the scenes, allowing developers to focus entirely on crafting the user experience. Companies like vivo, Intellitek Health, and Lingopal have also shared positive feedback on 3.5 Transcribe, highlighting its impressive latency, accuracy, and expansive language support. Start using 3.5 Transcribe today For developers : In public preview in the Gemini API via Google AI Studio and Google Antigravity . For enterprises : In public preview via Gemini Enterprise Agent Platform and coming soon to Gemini Enterprise for Customer Experience . For everyone : In Gemini app on macOS in English, Rambler on Android in select countries and languages , and coming soon to Chrome. Get the latest news from Google in your inbox Sign up for our newsletters with product updates, event information, special offers, and more. Your information will be used in accordance with Google's privacy policy. You may opt out at any time.