Unverified50% confidenceBenchmarkExact time
In simulation experiments, Turbo's streaming TTS was about 3.5 times faster than batch TTS at 20 tokens, and about 14 times faster at 80 tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
Unverified在高并发场景下，一个平均延迟180ms的TTS服务大约每8次响应就有1次飙到400ms以上68% similarUnverifiedAmong the top ten models, TTFT ranges from 748.61 seconds to 2.82 seconds, a difference of up to 265 times.68% 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68% similarUnverifiedtps (tokens per second) is a core metric for measuring model inference speed: below 30 tps you will clearly feel the wait, 60-100 tps can satisfy most dialogue and coding needs, and above 100 tps is quite smooth.67% similarVerifiedTPS measurement is typically divided into two phases: Time to First Token (TTFT) and the generation rate (throughput) of subsequent tokens.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1020010API
curl https://kongchang.com/api/v1/knowledge/claims/1020010MCP
get_claim(id=1020010)