Gemini 3.5 Transcribe 正式可用,推出两款语音转文字模型
原标题:August 26, 2026
AI 摘要
Google 在 Gemini API 发布说明中宣布,Gemini 3.5 Transcribe 正式可用(GA),推出两款基于 Gemini 音频理解能力的专用语音转文字模型。gemini-3.5-transcribe 面向高精度、低延迟的非流式转写,支持 85 种以上语言的语句级语言检测、说话人分离、词级时间戳和最多 1000 词的自定义词表偏置;gemini-3.5-transcribe-live 通过 Live API 在 WebSockets 上提供低延迟双向流式转写,支持中间与最终转写事件、Smart transcription 模式及多种 VAD 策略。
正文节选
Gemini 3.5 Transcribe generally available (GA): Released two dedicated speech-to-text models based on Gemini's audio understanding: Gemini 3.5 Transcribe ( gemini-3.5-transcribe ): High-accuracy, low-latency non-streaming speech-to-text with utterance-based language detection across 85+ languages, speaker diarization, word-level timestamps, and custom vocabulary biasing (up to 1,000 terms). Gemini 3.5 Transcribe Live ( gemini-3.5-transcribe-live ): Low-latency, bidirectional streaming speech-to-