Unverified50% confidenceFactExact time
The original statement mentions "we deploy voice models physically close to reasoning models," i.e., deploying voice models physically close to reasoning models.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/26/2026
First Seen
Valid until: 1/24/2027
Sources
Related Entities
Related Claims
UnverifiedAfter removing the acoustic tokenizer, the model must model directly in a continuous acoustic space, typically relying on continuous generation paradigms such as diffusion models or flow matching, which shortens the inference pipeline.76% similarUnverifiedThe background reasoning mechanism decouples time-consuming reasoning computation from the real-time audio stream, allowing the model's voice response layer and reasoning computation layer to run in parallel74% similarUnverified流式推理技术让模型对持续到来的音频帧进行增量式处理，在达到足够置信度时立即开始输出，而非等待说话人完整停顿71% similarUnverifiedAligned models tend to proactively introduce disclaimers or interrupt conversation flow when handling hypothetical reasoning and role-playing tasks, behaviors that are almost nonexistent in base models.68% similarUnverified传统大模型生成是自回归的，必须生成完整序列才能输出，而实时语音场景要求模型在接收输入的同时开始生成输出67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1099142API
curl https://kongchang.com/api/v1/knowledge/claims/1099142MCP
get_claim(id=1099142)