Unverified50% confidenceBenchmarkExact time
Among the top ten models, TTFT ranges from 748.61 seconds to 2.82 seconds, a difference of up to 265 times.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedAt approximately 4K input, TTFT is 23.6 seconds with decoding at 46.6 tok/s; at 8K, 47 seconds and 41.4 tok/s; at 16K, 1 minute 30 seconds and 30.8 tok/s; at 30K, 3 minutes 15 seconds and 31.9 tok/s.76% similarUnverifiedThe cumulative latency of a traditional ASR→LLM→TTS three-stage pipeline is typically between 800 milliseconds and 2 seconds.75% similarUnverifiedWhen current mainstream large models handle complex code tasks, the time to first token (TTFT) is often between 2 and 8 seconds.73% similarUnverified三明治架构相比原生Speech-to-Speech多了两次转换环节，STT环节通常增加100-300毫秒，TTS环节增加100-200毫秒73% similarUnverifiedOn a 16G GPU, a 60-second audio clip takes only 101 seconds with 512-frame chunking, 231 seconds with 1024-frame chunking, and 285 seconds without chunking.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1005260API
curl https://kongchang.com/api/v1/knowledge/claims/1005260MCP
get_claim(id=1005260)