Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.medera.info/llms.txt

Use this file to discover all available pages before exploring further.

Computes vocal prosody features from audio for downstream agent reasoning. Inputs: audio stream or recording (≥ 10 s, 16 kHz) Outputs: F0, jitter, shimmer, HNR, speaking rate, prosodic flatness, confidence See Vocal Acoustic Engine.