AUDIO · DIARIZATION

Speaker Diarization

Detect speaker-turn boundaries via audio energy analysis — processed on-device in your browser. No upload.

Select or drag an audio fileDrag & DropProcessed on your device — never uploaded or stored

Sensitivity Threshold — -40 dB

-60 dB (sensitive)-20 dB (less sensitive)

Min. Segment Gap — 1.5s

0.5s5.0s

⚠ Energy-based segmentation only — true speaker identification (embedding-based) is not yet supported. Segments are alternately assigned Speaker 1 / 2 at silence boundaries.

Upload an audio file and run to see speaker segments.

Share your feedback on this tool

Used 0 times so far