Back to the siteAM.

03 · Hindi / Hinglish voice assistant

TITAN

A JARVIS-style assistant for Windows: say "Hey Titan" in Hindi, Hinglish or English, and it does the job on the laptop — then answers in English.

3-lane LLM fallback
Step inside the 3D room

What it is

Always-on speech recognition with voice activity detection, a fuzzy-matched wake word, barge-in and turn detection that waits out half-finished Hinglish sentences. The brain is an LLM with a three-lane fallback, and function calling turns each request into a real action on the PC.

How it works

Say "Hey Titan" and ask in Hindi, Hinglish or English: the request becomes an LLM function call and lands on the desktop as a real action, and TITAN answers out loud in English.

  1. 01

    "Hey Titan"

    always-on speech recognition; the wake word is fuzzy-matched (Levenshtein plus known mishears)

  2. 02

    Listening

    voice activity detection, streaming Whisper transcription, and turn detection that waits out half-finished Hinglish sentences

  3. 03

    The brain

    Llama 3.3 70B on NVIDIA, falling back to Groq, then Gemini 2.5 Flash, silently

  4. 04

    Function calling

    the LLM returns { action, args, speak } and a dispatcher runs it

  5. 05

    A real action

    apps, websites, YouTube, web search, weather, files, volume, lock, sleep, screenshots

  6. 06

    A spoken reply

    Google Cloud Neural2 voice (browser voice as backup); interrupt it any time by speaking

By the numbers

3

LLM lanes, switching silently

"Boss"

what it calls Ayush

127.0.0.1

only: no website or device can reach it

What I built

  • Three-lane LLM fallback — NVIDIA (Llama 3.3 70B), then Groq, then Gemini 2.5 Flash — switching silently when one fails
  • Wake word "Hey Titan" with Levenshtein fuzzy matching for mishears, barge-in, and semantic turn detection for English and Hinglish
  • Actions: open and close apps, search sites, play on YouTube, web search, weather, file search, volume, lock, sleep, screenshots — each reports success or failure out loud
  • Memory that survives restarts (reminders, notes, long-term facts with atomic writes); the server listens only on 127.0.0.1 with CORS locked

Under the hood

Memory

  • Reminders that aren't lost when the tab closes
  • Notes, and long-term facts that survive restarts
  • Short-term memory of the last 3 turns, so "play that again" works

Reliability

  • Every action reports success or failure, and failures are spoken, never silent
  • Atomic JSON writes, so a crash can't corrupt memory
  • Server bound to 127.0.0.1 with CORS locked

Stack

  • React
  • Vite
  • Tailwind CSS
  • Node.js
  • Express
  • Whisper
  • Llama 3.3 70B
  • Groq
  • Gemini
  • Google Cloud TTS
  • PowerShell