Baran Can Aydın·4h agoBuilding My Own ESP32 Voice Assistant — Part 7: Soldering and the First SoundThis is part 7 of an ongoing series in which I build my own ESP32 voice assistant. I add new parts as the components arrive and the project…
Sachin Chaurasiya·1d agoVoice Agents Deep Dive Part 1: Digital Audio Fundamentals, Sample Rates, Bit Depth and FormatsYou cannot build a voice agent that listens or speaks until you understand the audio it handles. This guide explains digital audio for…
Daniel James·1d agoMy Voice Memos Were a Graveyard Until I Switched to Speech to TextI get my best ideas while driving, which is the worst time to have them. So for years I talked into my phone, felt very smart, and never…A response icon2A response icon2
Sachin Chaurasiya·1d agoVoice Agents Deep Dive Part 0: The Voice AI Landscape and How Machines Hear and SpeakMost developers picture voice AI as a chatbot with a microphone, then hit a wall when latency, audio, and speech recognition all have to…
InTowards AIbyLaura Verghote·4d agoBuild a Dual-Mode Voice Agent in Microsoft Foundry with Native SubagentsFree full article for non-Medium members — here
Mayank Jhunjhunwala·4d agoI tried to build a voice assistant that lives on my PC. Part 1A one-day experiment with local AI, a gaming PC, and a lot of “wait, why did it do that?”
Ranjith rosan·4d agoI built Quasnooze, a local-by-default personal AI assistant in plain Node.jsOver the past few weeks I have been building Quasnooze, an MIT-licensed personal AI assistant designed to run on your own machine without…
Isabel Fisher·5d agoI Gave My Voice Agent a Face, and It Runs Entirely on My Own GPUA hands-on look at self-hosting OpenSpline, from one install command to a live talking avatar
InAgora.iobyjingyi·5d agoArchitecture Tradeoffs in Native Audio, Transcription, and Tool CallingIn our recent Agora × Google Discord livestream, Thor from Google DeepMind and Hermes from Agora discussed a recurring question in voice…
AgenticAITalks·6d agoHow We Built a Hindi Voice AI with Sarvam and LiveKitThe models, architecture, and conversation design behind an AI that listens, checks information, and speaks back.
