Google 发布 Gemini 3.5 Transcribe，支持 85 种语言实时语音转文字

Google's Gemini 3.5 Transcribe turns speech to text in 85 languages while auto-correcting your verbal stumbles

AI 导读

Google 推出 Gemini 3.5 Transcribe 语音转文字模型，支持 85 种以上语言，可自动去除“um”等填充词、纠正口误并自动排版。流式转录词错误率为 4.0%，录音音频为 2.6%，延迟较前代 Chirp 3 降低 70%。

正文 · 原文

Google has launched Gemini 3.5 Transcribe, a speech-to-text model for real-time transcription. It recognizes over 85 languages automatically, strips filler words like "um," corrects slips of the tongue, and formats text on its own. Google reports a word error rate of 4.0 percent for streaming and 2.6 percent for recorded audio, with 70 percent lower latency than its predecessor, Chirp 3. Through "function calling," the model can hand off tasks like image generation or web searches to other Gemini models.

视频 · 前往原文观看

The model ships with two interfaces.The Live API handles real-time streaming with very low latency (gemini-3.5-transcribe-live), while the Interactions API processes recorded audio with speaker attribution and timestamps (gemini-3.5-transcribe). The model is live in Google AI Studio and on the Gemini Enterprise Agent Platform. It's already built into Gboard for Android (via "Rambler") and the Gemini app on macOS, with Chrome support coming soon.