Unverified50% confidenceFactExact time
Voxtral's audio encoder produces one audio token every 80 milliseconds, i.e., a fixed frame rate of 12.5 tokens per second.
1
Sources
50%
Confidence
Long-term
Relevance
10/3/2026
First Seen
Sources
Related Entities
Related Claims
Unverified人类语音传递信息的速率约为每秒39比特，而六轴机械臂的控制信号带宽可达数千比特每秒78% similarUnverifiedThe cross-correlation coefficient between the output audio envelope and the separated vocals reaches 0.944 with a delay of approximately 0 ms, but the author clarifies this only proves that fully_copy transferred the audio in full sync and is not a measure of lip-sync accuracy.75% similarUnverifiedThe sampling rate of audio signals is typically 16 kHz or 44.1 kHz, containing tens of thousands of sample points per second, while the output text sequence contains only approximately 3–5 words per second.74% similarUnverifiedAt each observed false start, the speech probability surges by more than nine orders of magnitude within a single 80-millisecond frame.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/969742API
curl https://kongchang.com/api/v1/knowledge/claims/969742MCP
get_claim(id=969742)