Unverified50% confidenceOpinionExact time
Among mainstream large models on the market, there are almost none that meet the requirement of native real-time multimodal input and output (input supporting speech, images, text and video, and output also multimodal including speech).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
VerifiedFor voice agents, multimodal large models must support not only voice, images, text, and video as inputs, but also voice as output.79% similarUnverifiedAccording to the sharer's own testing, truly mature and stable real-time voice multimodal large models that are ideal choices are almost nowhere to be found on the market, whether domestic or foreign.72% similarUnverifiedPlus版本主打高质量生成，牺牲一定实时性以换取更高音质，适合有声书、播客、影视配音等场景69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036761API
curl https://kongchang.com/api/v1/knowledge/claims/1036761MCP
get_claim(id=1036761)