Unverified50% confidenceReleaseExact time
字节豆包发布了Seed Audio 1.0音频生成模型
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/23/2026
First Seen
Valid until: 10/21/2026
Sources
Related Claims
Unverified字节跳动的Seed Audio是其自研的多模态音频生成大模型，基于扩散模型与大规模音频预训练技术82% similarUnverifiedSeed Audio 1.0支持20多种语言79% similarUnverified实测者使用Seed Audio生成了一首男女对唱的MV配乐77% similarUnverified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75% similarUnverifiedDiffusers支持AudioLDM等音频扩散模型，能够根据文本描述生成音乐和音效68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/598704API
curl https://kongchang.com/api/v1/knowledge/claims/598704MCP
get_claim(id=598704)