Unverified50% confidenceFactExact time
Oído's firmware runs on a single core at 1.97 times the speed of audio duration, meaning a 4-second instruction can only be transcribed approximately 8.7 seconds after it is finished being spoken.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDuring the second-pass stage, using two denoising steps took approximately 700-plus seconds, while three steps increased the time to over 1,000 seconds.75% similarUnverifiedFour capability test results: song generation producing 175 seconds of audio, audio-to-score transcription of a 4-second source taking 36 seconds, sheet music rendering outputting a PDF and a playback audio file, and reference voice timbre completed in 47 seconds.74% 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% 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.72% similarVerifiedThe end-to-end latency of full-duplex voice AI must be controlled within 150 milliseconds; otherwise the human ear will perceive a noticeable lag.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001257API
curl https://kongchang.com/api/v1/knowledge/claims/1001257MCP
get_claim(id=1001257)