wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

address feedback.

Browse Source
This commit is contained in:
Gökmen Görgen
2026-01-20 14:11:00 +01:00
parent 0e99400148
commit 0a8588669c
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/pipecat/audio/vad/aic_vad.py
View File

@@ -30,12 +30,14 @@ class AICVADAnalyzer(VADAnalyzer):
Range: 0.0 to 20x model window length Range: 0.0 to 20x model window length
Default (SDK): 0.05s (50ms) Default (SDK): 0.05s (50ms)
- minimum_speech_duration: - minimum_speech_duration:
Controls for how long speech needs to be present in the audio signal before the VAD considers it speech (in seconds). Controls for how long speech needs to be present in the audio signal before the
VAD considers it speech (in seconds).
Range: 0.0 to 1.0 Range: 0.0 to 1.0
Default (SDK): 0.0s Default (SDK): 0.0s
- sensitivity: - sensitivity:
Controls the energy threshold sensitivity. Higher values make the detector Controls the sensitivity (energy threshold) of the VAD. This value is used by
less sensitive (require more energy to count as speech). the VAD as the threshold a speech audio signal's energy has to exceed in order
to be considered speech.
Range: 1.0 to 15.0 Range: 1.0 to 15.0
Formula: Energy threshold = 10 ** (-sensitivity) Formula: Energy threshold = 10 ** (-sensitivity)
Default (SDK): 6.0 Default (SDK): 6.0