Unverified85% confidenceEventTime unknown
字节跳动发布了端到端同声传译模型Seed Live Interpret 2.0，在中英语音同传的延迟和准确率上接近人类水平，并支持零样本声音复刻
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Claude Code子智能体与Cursor BugBot发布：AI编程工具全面升级
bilibili橘鸦Juya
Related Entities
Related Claims
Unverified字节豆包发布了Seed Audio 1.0音频生成模型75% similarUnverifiedOpenAI 开源的 Whisper 模型在 99 种语言上实现接近人类水平的词错率，并原生支持时间戳输出73% similarUnverifiedOpenAI最新发布的语音模型能够一边听一边说，几乎实现零延迟的双向对话71% similarUnverifiedOpenAI开源的Whisper模型大幅提升了识别准确率，whisper.cpp、faster-whisper等移植版本将本地推理延迟压缩至实时以下71% similarVerified现代零样本或少样本声音克隆技术仅需几秒到几分钟的参考音频，就能生成高度逼真的目标说话人语音70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4224API
curl https://kongchang.com/api/v1/knowledge/claims/4224MCP
get_claim(id=4224)