DEV Community

Cover image for Building Revora AI โ€” My 10-Day Voice Agent Journey ๐Ÿš€
Aadarsh Jain
Aadarsh Jain

Posted on

Building Revora AI โ€” My 10-Day Voice Agent Journey ๐Ÿš€

๐Ÿš€ Building Revora AI: My 10-Day Voice Agent Journey

From a raw audio pipeline to an intelligent, multilingual, multi-agent AI learning companion for Bharat.


๐Ÿ“Œ Project Highlights & Hackathon Track

  • Challenge: 10 Days of Voice Agents โ€” #VoiceForBharat Edition by Murf AI
  • Track: ๐Ÿ“š Learning & Literacy
  • Voice Engine: โšก Murf Falcon (Ultra-low latency multilingual TTS)
  • Real-Time Transport: ๐ŸŽ™๏ธ LiveKit WebRTC
  • Database & Memory: ๐Ÿ˜ Supabase (PostgreSQL + Knowledge State)
  • GitHub: https://github.com/AadarshJain07/murf-livekit-starter

๐ŸŒŸ The Vision: Why Voice-First Learning for Bharat?

In India, learning has always been conversational. When students study, they don't think in rigid text prompts โ€” they discuss, debate, ask doubts, and switch effortlessly between English, Hindi, and Hinglish.

Yet, most modern AI tutors are text-locked:

  1. Friction in Expression: Typing complex mathematical equations, chemical formulas, or nuanced conceptual doubts on a mobile keyboard kills curiosity.
  2. Language Barrier: Rigid single-language interfaces fail Indian students who naturally code-switch ("Bhaiya, Doppler effect mein apparent frequency increase kab hoti hai?").
  3. Passive Consumption: Text chatbots output overwhelming paragraphs that students skim rather than truly understand.

Revora AI was built to bridge this gap. Created over 10 intense days during the Murf AI #VoiceForBharat challenge, Revora turns learning into an active, real-time, voice-first dialogue where students simply talk, ask, practice, debate, and master concepts naturally.


๐Ÿ—บ๏ธ The 10-Day Build Roadmap

Day 1โ€“2 โ”€โ”€โ”€โ”€โ”€โ”€โ–บ Day 3โ€“4 โ”€โ”€โ”€โ”€โ”€โ”€โ–บ Day 5โ€“6 โ”€โ”€โ”€โ”€โ”€โ”€โ–บ Day 7โ€“8 โ”€โ”€โ”€โ”€โ”€โ”€โ–บ Day 9โ€“10
 Voice Core      Personality     Long-Term       Actionable      Multi-Agent
 & LiveKit       & Pedagogical   Memory &        Tools & Live    Specialists &
 Streaming       Guardrails      Gamification    Telemetry       Debate Mode
Enter fullscreen mode Exit fullscreen mode
Phase Milestone & Focus Key Tech / Breakthrough
Days 1โ€“2 Voice Pipeline Foundations Real-time audio streaming over LiveKit WebRTC + Murf Falcon TTS integration
Days 3โ€“4 Pedagogical Persona & Guardrails Socratic teaching style, safe educational guardrails, interruptibility & latency tuning
Days 5โ€“6 Long-Term Memory & Gamification Supabase session tracking, XP rewards, Quests & diagnostic weakness detection
Days 7โ€“8 Actionable Tools & Telemetry Tool calling, automated parent/student check-in calls, real-time analytics dashboard
Days 9โ€“10 Specialist Agent Swarm & Debate Mode Domain expert handoffs (Maths, Physics, Chemistry) + Adversarial Debate Mode

๐Ÿ—๏ธ System Architecture & Workflow

Revora combines real-time WebRTC audio streaming, large language model reasoning, persistent knowledge graphs, dynamic tool execution, and specialized domain agents into a cohesive learning experience.

                                  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                                  โ”‚      ๐ŸŽ™๏ธ Student Voice       โ”‚
                                  โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                                 โ”‚
                                                 โ–ผ
                                  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                                  โ”‚       LiveKit WebRTC        โ”‚
                                  โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                                 โ”‚
                                                 โ–ผ
                                  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                                  โ”‚     Speech-to-Text (STT)    โ”‚
                                  โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                                 โ”‚
                                                 โ–ผ
                     โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                     โ”‚            Revora Agent Orchestrator & Router         โ”‚
                     โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                            โ”‚               โ”‚               โ”‚         โ”‚
             โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”      โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”  โ”Œโ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
             โ”‚ ๐Ÿง  Memory & DB โ”‚      โ”‚  ๐Ÿ› ๏ธ Tools  โ”‚  โ”‚ ๐Ÿ“Š Stats โ”‚  โ”‚ ๐Ÿ‘ฅ Specialists    โ”‚
             โ”‚   (Supabase)   โ”‚      โ”‚ (Actions)  โ”‚  โ”‚(Analyticsโ”‚  โ”‚  (Domain Swarm)  โ”‚
             โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜      โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜  โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜  โ””โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                                                      โ”‚
                                     โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                                     โ”‚ Samar (Maths)                  โ”‚ Pooja (Physics)                โ”‚
                                     โ”‚ Abhinav (Chemistry)            โ”‚ Debate Specialist (Socratic)   โ”‚
                                     โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                                 โ”‚
                                                 โ–ผ
                                  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                                  โ”‚   Murf Falcon Streaming TTS โ”‚
                                  โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                                 โ”‚
                                                 โ–ผ
                                  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                                  โ”‚     ๐Ÿ”Š Voice Response       โ”‚
                                  โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
Enter fullscreen mode Exit fullscreen mode

๐Ÿ’ก Deep Dive: Core Innovations & Features

1. ๐ŸŒ Multilingual Voice & Code-Switching (English โ€ข Hindi โ€ข Hinglish)

Students in Bharat rarely speak pure Queen's English or formal textbook Hindi. Revora is engineered to recognize Indian phonetic nuances and respond with natural bilingual fluidity.

Student: "Sir, mujhe photoelectric effect ka threshold frequency samajh nahi aaya, please simple Hindi mein samjhao na?"

Revora (via Murf Falcon): "Bilkul! Dekho, threshold frequency woh minimum energy barrier hai jo electron ko metal surface se bahar nikalne ke liye chahiye. Agar light ki frequency isse kam hui, toh chahe kitni bhi bright light daal do, koi electron bahar nahi aayega!"


2. ๐Ÿ‘ฅ Specialist Agent Swarm with Zero-Context Loss Handoff

Rather than relying on a single generic prompt that tries to do everything, Revora implements an explicit routing architecture to domain-specific specialist agents:

  • ๐Ÿ“ Samar (Mathematics Specialist): Step-by-step algebraic breakdowns, mental math shortcuts, and geometric visualization.
  • โš›๏ธ Pooja (Physics Specialist): Intuitive thought experiments, kinematics, thermodynamics, and real-world mechanics.
  • ๐Ÿงช Abhinav (Chemistry Specialist): Reaction mechanisms, periodic trends, stoichiometry, and molecular structures.
  • ๐ŸŽ™๏ธ Debate Specialist: Socratic sparring partner for structured argumentation, evidence assessment, and critical thinking.

๐Ÿ”„ How Contextual Handoff Works:

When a student says "Connect me to the Physics Specialist," Revora doesn't simply switch models โ€” it packages the entire conversation state, current topic, and student learning profile:

# Conceptual Agent Handoff Handler
async def route_to_specialist(student_id: str, specialist_name: str, conversation_ctx: dict):
    # 1. Fetch persistent learner profile from Supabase
    learner_profile = await supabase.table("student_profiles").select("*").eq("id", student_id).single()

    # 2. Package handoff state payload
    handoff_payload = {
        "student_name": learner_profile["name"],
        "mastery_level": learner_profile["mastery_level"],
        "weak_areas": learner_profile["weak_areas"],
        "current_topic": conversation_ctx.get("current_topic"),
        "recent_dialogue": conversation_ctx.get("history")[-5:]
    }

    # 3. Voice announcement before handoff
    await agent.speak(f"Switching you over to {specialist_name}, who has your context ready.")

    # 4. Activate specialist with preserved state
    return await activate_specialist_agent(specialist_name, handoff_payload)
Enter fullscreen mode Exit fullscreen mode

Key Benefit: The student never has to repeat their question or explain where they got stuck.


3. ๐Ÿง  Memory & Gamified Closed-Loop Learning Engine

Revora goes far beyond a passive conversational bot by embedding a continuous learning feedback loop:

๐Ÿ”„ Learn โž” Practice โž” Measure โž” Diagnose Weakness โž” Targeted Quests

  • ๐ŸŽฏ Interactive Quests: Generates short 2-minute voice quizzes tailored to the student's current topic.
  • โญ XP & Mastery Badges: Provides instant positive reinforcement upon completing concepts.
  • ๐Ÿ” Diagnostic Weakness Engine: Tracks recurring mistakes in Supabase PostgreSQL and automatically schedules spaced-repetition reinforcement during subsequent sessions.

4. โš”๏ธ Socratic Debate Mode: Building Critical Thinkers

Most educational AI simply gives direct answers, encouraging passive memorization. Revora's Debate Mode trains students to defend their ideas:

  1. The student chooses a debate topic (e.g., "Should AI replace traditional examinations?" or "Is nuclear power the best clean energy solution for India?").
  2. The AI takes the counter-position, challenging premises and demanding supporting evidence.
  3. At the end of the round, the AI provides a constructive scorecard evaluating Reasoning, Evidence, Counterargument Handling, and Clarity.

5. ๐Ÿ› ๏ธ Actionable Tools & Real-Time Telemetry

Revora is an agent with hands. Using function calling, it can:

  • Query student learning history and update mastery graphs in Supabase.
  • Trigger automated outbound progress calls to students or parents.
  • Escalate to human mentors when a student shows severe confusion or distress.
  • Stream live call performance metrics into an analytics dashboard.

๐Ÿ“Š Live Benchmark Metrics:

Metric Benchmark Result Status
Total Test Calls 14 โœ…
Successful Completions 12 ๐Ÿš€
Graceful Fallbacks / Handled Errors 2 ๐Ÿ›ก๏ธ
Call Success Rate 85.7% ๐Ÿ“ˆ
TTS Synthesis Latency (Murf Falcon) ~250ms โšก

๐Ÿ› ๏ธ Build Your Own Voice Agent: Technical Blueprint

If you are building your own production-grade voice agent, here are the four foundational pillars:

  1. Speech-to-Text (STT): Captures microphone input and converts it into a real-time text stream with low word-error rates.
  2. LLM Orchestration: Understands intent, accesses memory, executes tool calls, and generates concise, conversational responses.
  3. Text-to-Speech (TTS): Converts text into ultra-realistic, low-latency audio chunks using Murf Falcon.
  4. Real-Time WebRTC Transport: Connects bidirectional audio streams using LiveKit for sub-second, interruptible voice interactions.

๐Ÿ” Secure Environment Configuration

Store all credentials in server-side environment variables:

# Murf AI Ultra-Low Latency Voice Engine
MURF_API_KEY="your_murf_api_key_here"

# LiveKit WebRTC Infrastructure
LIVEKIT_API_KEY="your_livekit_key"
LIVEKIT_API_SECRET="your_livekit_secret"
LIVEKIT_URL="wss://your-project.livekit.cloud"

# Supabase Vector & State Database
SUPABASE_URL="https://your-project.supabase.co"
SUPABASE_SERVICE_ROLE_KEY="your_supabase_service_role_key"
Enter fullscreen mode Exit fullscreen mode

[!CAUTION]
Security Best Practice: Never expose private API keys or database service role keys in frontend client bundles or public GitHub repositories. All agent routing and database mutations must execute server-side.


๐Ÿ”ฎ What's Next for Revora AI?

This 10-day challenge established the core voice engine. Here is what is on the roadmap:

  • [ ] ๐Ÿ–ผ๏ธ Multimodal Whiteboard Sync: Enable students to sketch math proofs or circuit diagrams on screen while speaking with Revora.
  • [ ] ๐Ÿ—ฃ๏ธ Regional Language Expansion: Expand beyond Hindi/Hinglish to native Tamil, Telugu, Marathi, and Bengali voice models.
  • [ ] ๐Ÿ“š NCERT / State Board Curriculum Alignment: Auto-generate syllabus-aligned quests and revision packs directly from standard textbooks.
  • [ ] ๐Ÿ“ฑ Low-Bandwidth Telephony Gateway: Bring Revora to rural students via standard phone calls (SIP / PSTN integration).

๐Ÿ’ญ Key Takeaways & Final Thoughts

Building Revora during this 10-day sprint reinforced a vital engineering truth:

A great voice agent is not just an LLM wired to a speaker.

It is a carefully crafted symphony of:

๐ŸŽ™๏ธ Voice + ๐Ÿง  AI Reasoning + ๐Ÿ’พ Memory + ๐Ÿ› ๏ธ Tools + ๐Ÿ“Š Analytics + ๐Ÿ‘ฅ Domain Specialists + ๐Ÿ“š Pedagogy

What started as a simple audio loop on Day 1 became an intelligent, empathetic, multi-agent learning mentor for Indian students.

A huge shoutout to Murf AI for spearheading the #VoiceForBharat initiative and making ultra-fast voice AI accessible with Murf Falcon!


๐ŸŽ™๏ธ Revora AI โ€” Learn by Talking. ๐Ÿ‡ฎ๐Ÿ‡ณ

Tags: #VoiceForBharat #10DaysOfVoiceAgents #MurfAI #VoiceAI #EdTech #AIForEducation #LiveKit #Supabase #MultiAgent

Top comments (0)