Detect human vs voicemail/IVR in real-time. Make smarter routing decisions in ~3 seconds using speech-to-text and ML classification.
$ voicedetect --analyze incoming_call.wav
Analyzing audio stream...
Speech detected: "Hi, you've reached John's voicemail..."
Classification: MACHINE (confidence: 94.2%)
Decision: HANGUP (latency: 2.8s)
WebSocket streaming for low-latency decisions. Get human/machine classification in approximately 3 seconds.
Uses cloud STT APIs (OpenAI Whisper, Deepgram). Run on any server without expensive hardware.
Each customer gets their own trained classifier, thresholds, and settings. Full isolation.
Drop-in replacement for Asterisk AMD. EAGI integration with simple configuration.
Upload audio samples, label them, and retrain your model. Improve accuracy over time.
Call stats, usage tracking, and detection metrics. Know how your system is performing.
Monitor your AMD performance with live statistics, usage tracking, and recent call activity all in one place.
Track all processed calls
High accuracy detection
Sub-second latency
Usage quota tracking
Search, filter, and analyze every call processed by VoiceDetect.
Upload samples, label them, and train a custom ML model for your specific use case.
Evaluate your trained model with text input or voice uploads before going live.
Deploy VoiceDetect to your ViciBox/VICIdial servers with a single command.
/etc/voicedetect.conf/var/lib/asterisk/agi-bin/voicedetect-test command for verification
Customize timing, confidence thresholds, and silence handling to match your call center's needs.
When a call is answered, audio is streamed to VoiceDetect via WebSocket in real-time.
Voice Activity Detection (VAD) identifies speech. Audio is transcribed using cloud STT APIs.
Your tenant-specific classifier analyzes the transcript and determines human vs machine.
Result returned via WebSocket. Route to agent or hangup - all within ~3 seconds.
VoiceDetect AMD is available as a hosted service or self-hosted solution. Contact us to discuss your requirements and get pricing.
Get in Touch