Unverified50% confidenceFactExact time
Gemini 3.5 Live Translate 将语音识别、语义理解、翻译和语音合成四个环节封装进同一个多模态大模型中联合优化
1
Sources
50%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
谷歌AI密集更新：Gemini 3.5实时翻译、NotebookLM升级与DiffusionGemma解析
twitterGoogleAI6/12/2026
Related Claims
UnverifiedGemini的语音生成模型目前基于Gemini 2.5，支持多语言和多口音输出83% similarUnverifiedGemini 3.5 Live Translate 采用端到端学习范式，将ASR、NLU、MT、TTS四个环节在同一多模态大模型中联合优化80% similarUnverifiedGemini 3.5 Live Translate 同时暴露了输入音频的转录（input transcription）接口79% similarUnverifiedGemini 3.1 Pro具备多轮对话中的状态追踪能力，能将用户的自然语言需求增量式地映射到已有代码结构上77% similarVerified谷歌发布了专为实时语音到语音翻译打造的 Gemini 3.5 Live Translate76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/238222API
curl https://kongchang.com/api/v1/knowledge/claims/238222MCP
get_claim(id=238222)