<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <channel>
    <title>DEV Community: aravind048</title>
    <description>The latest articles on DEV Community by aravind048 (@aravind048).</description>
    <link>https://dev.to/aravind048</link>
    <image>
      <url>https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F1056618%2Fbbfd9101-8a9c-49a1-845c-ab2a0f2acc5f.png</url>
      <title>DEV Community: aravind048</title>
      <link>https://dev.to/aravind048</link>
    </image>
    <atom:link rel="self" type="application/rss+xml" href="https://dev.to/feed/aravind048"/>
    <language>en</language>
    <item>
      <title>STEM Tutor Voice Agent</title>
      <dc:creator>aravind048</dc:creator>
      <pubDate>Sun, 27 Jul 2025 05:38:47 +0000</pubDate>
      <link>https://dev.to/aravind048/stem-tutor-voice-agent-2ik6</link>
      <guid>https://dev.to/aravind048/stem-tutor-voice-agent-2ik6</guid>
      <description>&lt;p&gt;&lt;em&gt;This is a submission for the &lt;a href="https://dev.to/challenges/assemblyai-2025-07-16"&gt;AssemblyAI Voice Agents Challenge&lt;/a&gt;&lt;/em&gt;&lt;/p&gt;

&lt;h2&gt;
  
  
  What I Built
&lt;/h2&gt;

&lt;p&gt;I built a Domain Expert Voice Agent that acts as a real-time STEM tutor. This voice agent helps users understand complex concepts in math, physics, and computer science, using a live microphone input and a responsive LLM-based tutor.&lt;/p&gt;

&lt;p&gt;The project addresses the Domain Expert prompt category by:&lt;/p&gt;

&lt;p&gt;Demonstrating deep domain expertise via a Hugging Face LLM (zephyr-7b-beta)&lt;/p&gt;

&lt;p&gt;Supporting multi-turn conversations&lt;/p&gt;

&lt;p&gt;Integrating Universal-Streaming API for low-latency, real-time speech-to-text conversion&lt;/p&gt;

&lt;p&gt;Providing meaningful and natural tutoring experiences through dialogue refinement, clarification handling, and context preservation.&lt;/p&gt;

&lt;h2&gt;
  
  
  GitHub Repository
&lt;/h2&gt;

&lt;p&gt;[&lt;a href="https://github.com/aravind048/AI-ML/tree/Assembly_AI" rel="noopener noreferrer"&gt;https://github.com/aravind048/AI-ML/tree/Assembly_AI&lt;/a&gt;]&lt;/p&gt;

&lt;h2&gt;
  
  
  Technical Implementation &amp;amp; AssemblyAI Integration
&lt;/h2&gt;

&lt;p&gt;This project uses the AssemblyAI Universal-Streaming API to deliver sub-300ms latency transcription for real-time voice interaction.&lt;/p&gt;

&lt;p&gt;🧩 Core Tech Stack&lt;/p&gt;

&lt;ul&gt;
&lt;li&gt;Python 3.10&lt;/li&gt;
&lt;li&gt;AssemblyAI Universal-Streaming (WebSocket)&lt;/li&gt;
&lt;li&gt;HuggingFaceH4/zephyr-7b-beta:featherless-ai via HuggingFace Router API&lt;/li&gt;
&lt;li&gt;pyttsx3 for text-to-speech feedback&lt;/li&gt;
&lt;li&gt;asyncio, websockets, sounddevice, numpy&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;🧠 Voice-to-LLM Pipeline&lt;br&gt;
&lt;/p&gt;

&lt;div class="highlight js-code-highlight"&gt;
&lt;pre class="highlight plaintext"&gt;&lt;code&gt;# Connect to AssemblyAI's Universal-Streaming WebSocket
async with websockets.connect(ASSEMBLY_WS_URL, extra_headers=headers) as ws:
    await send_audio(ws)  # Stream microphone audio
    await receive_transcripts(ws)  # Get live transcription
&lt;/code&gt;&lt;/pre&gt;

&lt;/div&gt;





&lt;div class="highlight js-code-highlight"&gt;
&lt;pre class="highlight plaintext"&gt;&lt;code&gt;# Forward user query to LLM for STEM tutoring
response = requests.post(HF_API, headers=headers, json={
    "model": "HuggingFaceH4/zephyr-7b-beta:featherless-ai",
    "messages": [
        {"role": "system", "content": "You are a helpful STEM tutor..."},
        {"role": "user", "content": transcript}
    ]
})

&lt;/code&gt;&lt;/pre&gt;

&lt;/div&gt;



&lt;p&gt;✅ AssemblyAI Highlights&lt;/p&gt;

&lt;ul&gt;
&lt;li&gt;Ultra-low latency streaming&lt;/li&gt;
&lt;li&gt;Intelligent endpointing for clear turn detection&lt;/li&gt;
&lt;li&gt;Works seamlessly with domain-specific terminology (e.g., "parabola", "Big O notation", "Planck constant")&lt;/li&gt;
&lt;/ul&gt;

</description>
      <category>devchallenge</category>
      <category>assemblyaichallenge</category>
      <category>ai</category>
      <category>api</category>
    </item>
    <item>
      <title>nodejs to python and vice-versa</title>
      <dc:creator>aravind048</dc:creator>
      <pubDate>Sat, 01 Apr 2023 07:46:54 +0000</pubDate>
      <link>https://dev.to/aravind048/nodejs-to-python-and-vice-versa-5ekb</link>
      <guid>https://dev.to/aravind048/nodejs-to-python-and-vice-versa-5ekb</guid>
      <description>&lt;p&gt;Hi all&lt;/p&gt;

&lt;p&gt;This is my first content.&lt;/p&gt;

&lt;p&gt;In local server,&lt;/p&gt;

&lt;p&gt;(data)MySQL ---&amp;gt; (Node.js) ---&amp;gt; Python(process) =&amp;gt; working&lt;/p&gt;

&lt;p&gt;Im stuck in reverse flow i.e., I cant send the processed values from python back to database.&lt;/p&gt;

&lt;p&gt;What will be the issues?&lt;/p&gt;

&lt;p&gt;Kindly help me resolve it&lt;/p&gt;

&lt;p&gt;Thank you &lt;/p&gt;

</description>
      <category>backend</category>
      <category>python</category>
      <category>node</category>
      <category>flask</category>
    </item>
  </channel>
</rss>
