Beta

Stack Sensei — AI Voice Mentor Platform

Voice-Native • Emotion-Aware • Failover-Resilient

Real interviews are spoken, not typed. Stack Sensei is a voice-native AI mentor that interviews you out loud: a three-tier TTS failover chain, emotion-aware speech synthesis, and 13 distinct mentor voices deliver adaptive technical questioning across TypeScript, Java, Linux, and security. An eight-provider bring-your-own-key LLM layer keeps the intelligence flexible, while exam mode grades your answers and issues one-year certificates.

Kotlin Spring Boot React AI Voice TTS
🎙️
3-Tier
Resilient TTS Failover Chain
🥋
13 Voices
Emotion-Aware AI Mentors
🤖
8 Providers
BYOK LLM Abstraction
The Challenge

Interview Prep Is Silent. Voice AI Is Fragile.

Technical interviews are spoken conversations under pressure — yet most prep tools make you type, and most voice stacks collapse the moment a single vendor hiccups.

🔇

Text-Only Practice, Spoken Interviews

You rehearse by typing, then get judged on how you explain architecture out loud. The core interview skill never gets trained.

📉

Single-Vendor Fragility

Most voice apps hardwire one TTS API. One outage or rate limit and the session goes silent mid-answer — exactly when trust matters most.

🤖

Flat, Robotic Delivery

One-size-fits-all synthesis sounds the same whether you nailed the question or bombed it. No encouragement, no energy, no mentor.

🔒

LLM Lock-In

Hardwiring a single model means one vendor's pricing, one vendor's latency, one vendor's outages — with no user control over keys or cost.

The Solution

A Voice-Native AI Sensei

Stack Sensei 🥋 treats voice as core infrastructure, not a bolt-on: a health-monitored failover chain, emotion-mapped synthesis, and a provider-agnostic intelligence layer keep the conversation flowing.

🗣️

Converse, Don't Type

A full voice loop: browser capture with voice-activity detection, ElevenLabs Scribe transcription with Whisper fallback, and a sensei that asks adaptive questions and speaks the follow-up back.

🛡️

Three-Tier TTS Failover

ElevenLabs WebSocket streaming as primary, self-hosted Kokoro on Fly.io's private network as secondary, OpenAI TTS as tertiary — with active health monitoring and metrics on every hop.

🎭

Emotion-Aware Synthesis

An EmotionContext engine maps five states — from supportive to extremely emotional — to distinct synthesis settings. The sensei sounds encouraging when you struggle and fired up when you deliver.

🔑

Bring Your Own Model

Eight LLM providers behind one abstraction — Claude, GPT-4o, Gemini, Mistral, DeepSeek, Qwen, Kimi, or local Ollama — with per-user keys, key validation, and per-user circuit breakers.

Voice as a First-Class System Layer

Four layers, one goal: spoken answers in, spoken mentorship out, with no single point of failure between them. Kotlin and Spring WebFlux keep the pipeline reactive end to end.

4
Layer 4
🖥️

Client Layer

React 18 single-page app where learners speak or type. Voice-activity detection knows when you've finished answering; streamed audio starts playing before synthesis completes.

⚛️React 18 + TS 5.3 🎚️Voice Activity Detection 🗂️Zustand + Vite 🎧Streaming Playback
Real-Time Stream
3
Layer 3
🎙️

Voice Pipeline

The signature layer: a three-tier TTS failover chain with health monitoring, a text preprocessor that makes technical content speakable, and dual-provider STT. Thirteen mentor voices each carry a Kokoro fallback ID so the persona survives failover.

🎤ElevenLabs WebSocket TTS 🔁Kokoro Self-Hosted Fallback 🎭5 Emotion States 📝Scribe + Whisper STT
Real-Time Stream
2
Layer 2
🧠

Intelligence Layer

An eight-provider BYOK abstraction (Claude Sonnet 4.5 by default, down to local llama3:8b) drives adaptive questioning, answer grading, and conversation branching, grounded by a 61-document curated knowledge base with keyword-relevance retrieval.

🤖8 LLM Providers (BYOK) 🧭Adaptive Difficulty 🌿Conversation Branching 📚61-Doc Knowledge Base
Real-Time Stream
1
Foundation
🏗️

Platform Foundation

Kotlin on Spring Boot 3.2 WebFlux with OAuth2 security and Caffeine caching; PostgreSQL 16 evolved through 10 Flyway migrations. Stripe handles payments, Sentry watches production, Fly.io runs it all — and jsPDF renders the certificates.

🌱Spring Boot 3.2 WebFlux 🐘PostgreSQL 16 + Flyway 💳Stripe Payments 🚀Fly.io + Sentry

The Voice Round-Trip

Every exchange travels a four-stage loop. Each stage has a fallback, so the conversation never dies mid-sentence.

01

Listen

Browser → STT

What Happens

  • Voice-activity detection ends the take automatically
  • Audio transcribed by ElevenLabs Scribe
  • OpenAI whisper-1 stands by as fallback
  • Text input always available as a first-class path
Checkpoint: A spoken answer becomes clean text
02

Think

LLM Layer

What Happens

  • Your chosen provider grades the answer
  • Adaptive engine picks the next question by difficulty
  • Conversation branching explores follow-up paths
  • 61-doc knowledge base grounds the domain
Checkpoint: A graded response plus an emotion context
03

Speak

TTS Failover Chain

What Happens

  • Text preprocessor makes code and markup speakable
  • EmotionContext tunes stability, similarity, style
  • ElevenLabs streams over WebSocket; Kokoro, then OpenAI on failure
  • Per-provider usage tracked, audio cached
Checkpoint: Audio streams to the browser as it is synthesized
04

Adapt

Session Engine

What Happens

  • Practice mode offers adaptive hints
  • Exam mode runs a 20-question certification
  • Interview mode simulates the real thing
  • Passing an exam issues a 1-year certificate
Checkpoint: Every session ends scored — exams end certified

Four Pillars of the Voice Stack

Each pillar closes a failure class of production voice AI: availability, expressiveness, identity, and operability.

🛡️

Resilient Failover

Availability

Controls

  • ElevenLabs primary — highest quality, WebSocket streaming
  • Kokoro secondary — self-hosted, zero cold start, model preloading
  • OpenAI tertiary — most reliable last resort
  • Continuous health monitoring on the self-hosted tier
Closes: mid-session silence from a vendor outage
🎭

Emotion Engine

Expressiveness

Controls

  • Five-state EmotionContext enum
  • Per-state stability, similarity, and style settings
  • SUPPORTIVE and ENCOURAGING for struggle moments
  • ENTHUSIASTIC and EXTREMELY_EMOTIONAL for wins
Closes: the robotic monotone that kills engagement
🥋

Mentor Voice System

Identity

Controls

  • 13 voices with structured gender, age, energy, style traits
  • Per-voice Kokoro fallback IDs — persona survives failover
  • Voice catalog served from a dedicated API
  • #13: "Luca Sensei", the founder's own wise, calm systems-architect persona
Closes: the generic, interchangeable assistant voice
📊

Observability & Ops

Operations

Controls

  • TTS metrics exporter and per-provider usage tracking
  • Streaming, generation, and download narration endpoints
  • Audio cache management API
  • Sentry across the whole platform
Closes: black-box voice costs and invisible failures

From Beta to Voice-First Platform

The full voice loop is live in beta. Each phase deepens intelligence and reach without compromising the failover-first foundation.

Now

Beta

Live Today

Delivered

  • Full voice loop with 3-tier TTS failover
  • Practice, Exam, and Interview modes across 4 domains
  • 8-provider BYOK LLM layer with circuit breakers
  • Stripe billing and 1-year certificates
Milestone: Voice-native mentoring in production beta
Next

Smarter Retrieval

In Design

Planned Deliverables

  • Vector-search retrieval to replace keyword relevance
  • Embeddings over the curated knowledge base
  • Expanded document coverage per domain
  • Retrieval-quality evaluation harness
Milestone: Semantically grounded questioning
Planned

Deeper Voice

Exploration

Planned Deliverables

  • Additional mentor personas beyond the current 13
  • Latency tuning across the failover chain
  • Richer per-emotion tuning from session feedback
  • Expanded narration coverage for onboarding and lessons
Milestone: A voice layer that keeps getting more human
Planned

Teams & Hiring

Exploration

Planned Deliverables

  • Organization accounts for engineering teams
  • Certification as a screening signal for hiring
  • Team dashboards over exam results
  • New domains beyond the initial four tracks
Milestone: From solo prep to team capability building

Who Wins with Stack Sensei

Learners get a mentor who talks back; teams get verifiable skills; builders get a reference voice architecture.

🧑‍💻

For Job Seekers

Practice out loud — the way real interviews actually happen
Adaptive hints in Practice mode; zero hand-holding in Interview mode
Four domains: TypeScript/React, Java/Spring, Bash/Linux, Ops/Security
A 20-question exam that ends in a 1-year certificate
🏢

For Engineering Teams

Certification exams turn "I know Spring" into a graded, dated credential
Interview mode doubles as low-stakes rehearsal for internal mobility
BYOK means your model, your keys, your cost controls
Domains map to the stacks teams actually run in production
🛠️

For AI Builders

A working reference for 3-tier TTS failover with health monitoring
Emotion-to-synthesis parameter mapping you can study end to end
Self-hosted Kokoro shows the cost/latency case for hybrid voice infra
8-provider abstraction with per-user circuit breakers, in production Kotlin

Ready to Build Voice-Native AI?

This is the voice engineering I bring to client work: failover chains that survive vendor outages, synthesis that carries emotion, and LLM layers that never lock you in. If your product needs a voice — or your interview pipeline needs a sensei — let's talk.

3-Tier
TTS Failover Chain
13 Voices
Emotion-Aware Mentors
8 Providers
BYOK LLM Layer