---
id: 20260827-T0-08
title: "Gemini 3.5 Transcribe发布：更智能的语音转文字"
title_en: "Google Launches Gemini 3.5 Transcribe for Smarter Speech-to-Text"
url: https://ai.daily.yangsir.net/daily/20260827-T0-08
issue_date: 2026-08-27
publish_date: 2026-08-26T17:01:00.000Z
category: release
source_name: "Google DeepMind Blog"
source_url: https://deepmind.google/blog/intelligent-transcription-with-gemini-3-5-transcribe/
---

# Gemini 3.5 Transcribe发布：更智能的语音转文字

Google DeepMind发布Gemini 3.5 Transcribe，提供更智能的语音转文字功能。该模型在嘈杂环境下、多说话人识别和专业术语处理上均有改进，能生成带标点和段落结构的准确转录文本。开发者可通过API调用该模型，应用于会议记录、字幕生成和语音助手等场景。

## English Version

**Google Launches Gemini 3.5 Transcribe for Smarter Speech-to-Text**

Google DeepMind released Gemini 3.5 Transcribe with improved speech-to-text capabilities. It handles noisy environments, multi-speaker recognition, and domain-specific jargon better, generating accurate transcripts with punctuation and paragraph structure. The model is available via API for meetings, subtitles, and voice assistants.

---

**来源**：[Google DeepMind Blog](https://deepmind.google/blog/intelligent-transcription-with-gemini-3-5-transcribe/)

**详情页**：https://ai.daily.yangsir.net/daily/20260827-T0-08

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*