Build Voice Agents. From Scratch

Source: https://voice-agents.vizuara.ai/

The Foundations course is an 8-day intensive live bootcamp that teaches you how to build production-grade voice agents from scratch. Over 8 days of 2-3 hour live sessions, you’ll go from zero to building a complete real-time voice agent that can listen, reason, and speak — using ASR, TTS, LLMs, tool calling, memory, and streaming pipelines.

This course is for engineers, developers, and AI/ML practitioners who want to understand how voice agents work under the hood rather than relying on black-box frameworks. You’ll cover the full stack: Speech-to-Text with Whisper and faster-whisper, Text-to-Speech with Piper and Coqui TTS, voice activity detection with Silero VAD, LLM reasoning for spoken interactions, tool calling and memory for agentic behavior, real-time streaming with WebSockets, production architecture, and a final end-to-end capstone project. Every concept is taught from scratch — no hand-waving — by Dr. Sreedath Panat (MIT PhD, IIT Madras gold medalist, co-author of the Manning bestseller “Build DeepSeek from Scratch”).

You receive code files, hand-written notes, slides, visual guides, PDF booklets, assignments, interactive quizzes, lifetime access to the live Zoom recordings, and a certificate of completion with a project showcase page.

By the end of the bootcamp, you’ll be able to build real-time, tool-using voice agents like AI receptionists, meeting assistants, research assistants, and desktop voice assistants — and you’ll deeply understand every component, which makes you far more effective even when using high-level frameworks like Pipecat or LiveKit later.

Archive File List

# Modified                Size        Packed  Name
#
#  Archive YrfiaSlfzbXdbkqpCo[ddpanda].rar
2026-06-22 14:23     198813709     181624752  Build Voice Agents From Scratch [Foundations]\Session 1 - Voice agent foundations\Lecture video 1.mp4
2026-06-22 03:02           291           192  Build Voice Agents From Scratch [Foundations]\Session 1 - Voice agent foundations\Other links.txt
2026-06-22 03:28        151566        108192  Build Voice Agents From Scratch [Foundations]\Session 1 - Voice agent foundations\session_01_voice_agent_colab.ipynb
2026-06-22 03:25      56354750      56354752  Build Voice Agents From Scratch [Foundations]\Session 1 - Voice agent foundations\Slides.rar
2026-06-22 15:46     298454167     277242960  Build Voice Agents From Scratch [Foundations]\Session 2 - ASR in depth\Lecture video 2.mp4
2026-06-22 04:36           288           208  Build Voice Agents From Scratch [Foundations]\Session 2 - ASR in depth\Other Links.txt
2026-06-22 03:43          7018          2208  Build Voice Agents From Scratch [Foundations]\Session 2 - ASR in depth\session_02_whisper_mic_basic_colab.ipynb
2026-06-22 03:52      52790926      52790928  Build Voice Agents From Scratch [Foundations]\Session 2 - ASR in depth\Slides.rar
2026-06-22 04:45     105721633     101087952  Build Voice Agents From Scratch [Foundations]\Session 2 additional material - transformer foundations\From RNNs to Transformers - Introduction to attention mechanism.mp4
2026-06-22 04:55     248538445     231663392  Build Voice Agents From Scratch [Foundations]\Session 2 additional material - transformer foundations\Implementing multi-head attention with tensors.mp4
2026-06-22 04:52     132512676     126924720  Build Voice Agents From Scratch [Foundations]\Session 2 additional material - transformer foundations\Introduction to Multi-head attention.mp4
2026-06-22 04:47     199965954     191317760  Build Voice Agents From Scratch [Foundations]\Session 2 additional material - transformer foundations\Introduction to self-attention  Implementing a simplified self-attention.mp4
2026-06-22 04:37           805           480  Build Voice Agents From Scratch [Foundations]\Session 2 additional material - transformer foundations\Other Links.txt
2026-06-22 04:50     295738353     283552048  Build Voice Agents From Scratch [Foundations]\Session 2 additional material - transformer foundations\Q, K, V intuition  Introduction to self attention with trainable weights.mp4
2026-06-22 04:41     228151819     220001472  Build Voice Agents From Scratch [Foundations]\Session 2 additional material - transformer foundations\The journey of a single token - Introduction to LLMs.mp4
2026-06-22 04:51     200799339     193270880  Build Voice Agents From Scratch [Foundations]\Session 2 additional material - transformer foundations\Understanding causal attention or masked self attention.mp4
2026-06-22 16:39     214928418     202691632  Build Voice Agents From Scratch [Foundations]\Session 2 additional material - transformer foundations\_Transformers foundations.mp4
2026-06-22 18:04     352759328     333420304  Build Voice Agents From Scratch [Foundations]\Session 3 - TTS in depth\Lecture video 3.mp4
2026-06-22 10:51           278           192  Build Voice Agents From Scratch [Foundations]\Session 3 - TTS in depth\Other Links.txt
2026-06-22 11:03       1985633       1368656  Build Voice Agents From Scratch [Foundations]\Session 3 - TTS in depth\session_03_tts_pipeline_colab.ipynb
2026-06-22 19:21     258435703     238918864  Build Voice Agents From Scratch [Foundations]\Session 4 - LLM the brain\Lecture video 4.mp4
2026-06-22 10:56           294           208  Build Voice Agents From Scratch [Foundations]\Session 4 - LLM the brain\Other Links.txt
2026-06-22 11:02         48909         10928  Build Voice Agents From Scratch [Foundations]\Session 4 - LLM the brain\Session_4_LLM_Brain_Lab.ipynb
2026-06-22 20:28     257150928     230964640  Build Voice Agents From Scratch [Foundations]\Session 5 - Tools and memory for the LLM reasoning layer\Lecture video 5.mp4
2026-06-22 11:00           418           272  Build Voice Agents From Scratch [Foundations]\Session 5 - Tools and memory for the LLM reasoning layer\Other Links.txt
2026-06-22 11:01         59808         16752  Build Voice Agents From Scratch [Foundations]\Session 5 - Tools and memory for the LLM reasoning layer\session_05_builder_colab.ipynb
2026-06-22 11:01         38121         10144  Build Voice Agents From Scratch [Foundations]\Session 5 - Tools and memory for the LLM reasoning layer\session_05_tools_memory_colab.ipynb
2026-06-22 21:34     251877889     234736224  Build Voice Agents From Scratch [Foundations]\Session 6 - Streaming, buffer and barge-in\Lecture video 6.mp4
2026-06-22 11:05           345           208  Build Voice Agents From Scratch [Foundations]\Session 6 - Streaming, buffer and barge-in\Other Links.txt
2026-07-16 16:41     390271377     364118768  Build Voice Agents From Scratch [Foundations]\Session 7 - Building the full voice agent from scratch\Lecture video.mp4
2026-07-06 10:58           511           304  Build Voice Agents From Scratch [Foundations]\Session 7 - Building the full voice agent from scratch\Links shared during the lecture.txt
2026-07-06 11:00        240555        240560  Build Voice Agents From Scratch [Foundations]\Session 7 - Building the full voice agent from scratch\nimbus-voice-agent-main.zip
2026-07-06 11:00         52496         52496  Build Voice Agents From Scratch [Foundations]\Session 7 - Building the full voice agent from scratch\nimbus-voice-agent-starter-main.zip
2026-07-06 10:59         86031         73232  Build Voice Agents From Scratch [Foundations]\Session 7 - Building the full voice agent from scratch\voice agent features.pdf
2026-07-16 12:00         22435          8800  Build Voice Agents From Scratch [Foundations]\Session 8 - Reducing latency, Speech-to-speech models, livekit and VAPI\Latency reduction plan md file.md
2026-07-16 12:00           432           272  Build Voice Agents From Scratch [Foundations]\Session 8 - Reducing latency, Speech-to-speech models, livekit and VAPI\Other Links.txt
2026-07-16 12:02         80649         20608  Build Voice Agents From Scratch [Foundations]\Session 8 - Reducing latency, Speech-to-speech models, livekit and VAPI\Product catalogue md file.md
2026-07-16 17:19     208018784     191861488  Build Voice Agents From Scratch [Foundations]\Session 8 - Reducing latency, Speech-to-speech models, livekit and VAPI\Session 8 lecture video.mp4
2026-06-22 11:41        203560        200480  Build Voice Agents From Scratch [Foundations]\thumbnail.png
#
# Total                   Size        Packed  Files
#                   3954264641    3714658928  49

Download Links

Password: cms.ddpanda.org

1 parts

YrfiaSlfzbXdbkqpCo[ddpanda].rar – 3.5 GB