AI 导读
Google DeepMind 更新 Gemini 的语音转写能力，新增对复杂电话号码、邮编和订单号的理解，可去除口头语并自动格式化文本，支持自定义词汇和 85+ 语言的自动检测。新能力已在 macOS 的 Gemini app 和 Android 的 Gboard 上线，开发者可在 Google AI Studio 和 Antigravity 中开始构建。配图显示其 FLEURS 流式语音识别错误率为 5.50%。
正文
Here’s what’s new:
🔵 It’s better at understanding complex phone numbers, postal codes, and order IDs – even in noisy environments.
🔵 It can remove filler words and auto-format your text.
🔵 It recognizes custom vocabulary so the model knows unique names and product titles.
🔵 It automatically detects and transcribes speech in 85+ languages.
Try it now in the @Geminiapp on macOS and Gboard on @Android.
Start building in @GoogleAIStudio and @Antigravity → https://t.co/lNlILGYFVy
来源：@GoogleDeepMind · x.com