Unverified50% confidenceFactExact time
90 milliseconds is the streaming first-packet metric (Time to First Byte), not the generation time for an entire speech segment.
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe time to first byte (TTFB) for streaming synthesis can typically be reduced to the level of a few hundred milliseconds.76% similarVerified800毫秒是语音代理端到端延迟的业界公认阈值，人类面对面对话回应延迟通常在200-500毫秒之间75% similarUnverifiedThe 90-second generation time depends on document size and retrieval scope, and is not a fixed value.72% similarUnverifiedPolling rate refers to the number of times per second a device reports its status to the host; 8000Hz means input is sampled 8,000 times per second, with a theoretical latency as low as 0.125 milliseconds.70% similarUnverified蓝牙音频转换过程通常引入40-200毫秒的延迟70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1111187API
curl https://kongchang.com/api/v1/knowledge/claims/1111187MCP
get_claim(id=1111187)