Voice detection that works

Our first attempt measured audio volume to detect speech. This failed immediately because keyboard clicks triggered false positives, quiet speakers were missed entirely, and background noise caused complete chaos.

We switched to Silero, a machine learning model that detects speech patterns instead of volume. It runs in the browser and filters out non-speech sounds automatically.

We added two-phase processing that starts transcribing at 250ms and confirms at 600ms. This prevents the system from interrupting candidates mid-thought while keeping response times fast enough to feel natural.

Stopping hallucinations

Whisper invents phrases like "Thanks for watching!" and "Subscribe to my channel" when you send it silence or background noise.

We built four-layer prevention:

Only transcribe actual speech patterns

Track when the avatar speaks to prevent echo

Require minimum duration and data size

Clean audio before transcription

This approach reduced false transcriptions by 99%.

Identity verification

Candidates upload a photo with their application. The system verifies they match that photo during the interview.

We built this using DeepFace and OpenCV so everything processes locally. There are no cloud APIs involved and no data storage issues, making the system GDPR compliant by design.

Anti-spoofing models detect printed photos, phone or tablet screens, video playback, and 3D masks. The system doesn't block real candidates, but it flags suspicious cases for human review.

Fair assessment

• English proficiency

Four questions assess fluency, vocabulary, comprehension, and grammar. CEFR scoring from Beginner to Native.

• Role fit

Three questions about experience and skills. Each references previous answers. Scored on experience relevance, technical depth, and communication.

Questions generate dynamically without templates. Every interview is unique but the scoring stays consistent.

We built this in 43 hours from concept to working prototype using Claude Code.

Technical achievements:

• Reduced speech recognition hallucinations by 99%
• Achieved sub-2-second response time that feels natural
• Reached 85%+ face matching accuracy on real candidates
• Achieved 99.8% anti-spoofing accuracy on live faces

Business impact:

• Automated 10-minute screenings that previously required manual interviewer time
• Created 24/7 availability with no scheduling friction
• Eliminated fake candidates through identity verification
• Removed interviewer bias through consistent assessment
• Standardized company presentation so every candidate gets the same information

Candidate experience:

• Candidates get instant interview access without waiting
• The evaluation process is fair and consistent
• Conversation feels natural instead of robotic
• Candidates receive immediate feedback on next steps

We're adding TeamTailor integration for recruiter workflows, creating a custom 10Clouds avatar, building technical coding assessments, developing enhanced analytics, and improving anti-spoofing detection.

Product vision: We're developing a white-label solution for enterprises, building a multi-company platform, creating custom assessment templates, and adding advanced analytics.