Unverified50% confidenceFactExact time
WhaleLife's "audiovisual understanding" skill has FFmpeg built in, uses a quantized SenseVoice plus a VAD model for local speech recognition, and uses a pure TypeScript algorithm for music analysis, extracting frames and audio in 30-to-60-second segments.
1
Sources
50%
Confidence
Long-term
Relevance
11/13/2026
First Seen
Sources
WhaleLife Open-Sourced: Giving AI an Independent Body
bilibili紫杉樹11/13/2026
Related Entities
Related Claims
UnverifiedThe prompt is precise down to a millisecond-level action timeline, and sound effects are described in the overall_soundscape section.67% similarUnverified"Sound" includes simulators that can be changed in real time, letting readers produce the conclusions with their own hands.67% similarUnverifiedThe typical voice cloning workflow has four steps: data collection, feature extraction (converting audio to mel spectrograms), model training, and inference.66% similarUnverifiedTellie 采用的语音识别跟随技术属于「强制对齐」(Forced Alignment)技术的实时应用变体,将麦克风输入的语音流与预设脚本进行动态比对66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1166405API
curl https://kongchang.com/api/v1/knowledge/claims/1166405MCP
get_claim(id=1166405)