Assessment

AI Interview System

Gated assessment pipeline combining automated coding evaluation, AI avatar interviews with offline TTS, and live recruiter sessions — all monitored by OS-level integrity verification through the Tauri desktop client.

Assessment Pipeline

StageTechnologyDetail
Stage 1: Coding AssessmentJudge0 CE + TauriOS-level process monitoring. Detects AI copilots, remote desktop, browser automation.
GateThreshold CheckCoding score meets minimum threshold? Pass → Stage 2. Fail → rejected.
Stage 2: AI Avatar Interviewsherpa-onnx + Supertonic 3Offline TTS, Web Speech API STT, 3D avatar with lip-sync. Adaptive questioning via LLM.
GateThreshold CheckAI assessment meets threshold? Pass → Stage 3. Fail → rejected.
Stage 3: Live RecruiterLiveKit SFUMulti-participant WebRTC. 80-150ms audio, 120-250ms video latency.
ReportIntegrity + CompetencyFused proctoring confidence + skill scores. Full evidence pack for recruiter.

Supertonic 3 TTS Specifications

ParameterValue
Parameters99 million
ONNX Assets404 MB total
Languages31
RuntimeCPU-only, no GPU required
Integrationsherpa-onnx Rust bindings
PrivacyFully offline, no network dependency

Speech Pipeline

ComponentTechnologyDetail
VADSilero ONNXEndpoint detection, streaming
STTWeb Speech APIBrowser WebView native stack
LLMGroqAdaptive questioning, 350-600ms
TTSSupertonic 3 ONNX INT8Offline, CPU, 31 languages
PlaybackAudio Init<50ms

LiveKit SFU Performance

80-150ms
Audio Latency
120-250ms
Video Latency
<300ms
Multi-User Sync
<15%
CPU (4 participants)