🎙️ Voice-native document intelligence using Gemini, ElevenLabs STT/TTS, and Datadog observability — turning text documents into spoken conversations.
-
Updated
Dec 27, 2025 - TypeScript
🎙️ Voice-native document intelligence using Gemini, ElevenLabs STT/TTS, and Datadog observability — turning text documents into spoken conversations.
A curated list of awesome things related to voice technology, voice-first, virtual assistants, Voice User Interface, and more
🤖A Voice-First Agentic AI for Government Schemes in Hindi. Built with LangGraph (State Machine), Groq (Llama-3), and EdgeTTS for low-latency, CPU-optimized inference without GPUs.
🎙️ Transform documents into interactive conversations using voice with VoiceDoc Agent, powered by Google Cloud, ElevenLabs, and Datadog.
This repository contains Models and their backend for different Alexa Skills.
Voice-first personal AI secretary — Telegram bot that remembers everything
Vyapar AI is an offline-first, multilingual AI platform that empowers local Indian market vendors with fair price discovery, transparent verification, and voice-based negotiation using real-time market intelligence.
WhatsApp-first marketplace for India's women artisans. Five Indian languages, voice-driven onboarding, certified-seller pipeline, end-to-end orders inside one app she already trusts. Built for the Sankalp/Code4Change hackathon.
AVRT™ — The first ethical voice middleware firewall for AI, built to score reasoning with SPIEL™ and THT™. SHA‑256 hashing + blockchain-ready proof system. Created by Jason Proper. © 2025 BGBH Threads LLC.
The Smart Packet Identity Layer (SPID) is a universal, AI-readable identifier system that links every Smart Packet to its origin, context, and purpose — enabling secure, structured retrieval of voice-ready content across platforms.
Voice-first personal assistant — speak to an AI agent that sends messages, remembers things, and sets timers. No apps, no screens.
Voice-first personal AI agent for everyone. Press Alt+Space. Speak. Done.
luminous_flow leverages a multi-layered AI pipeline to deliver personalized, privacy-first financial insights and voice-first productivity features:
Voice-first Android memory assistant with on-device AI, Room, Jetpack Compose, and a local-first privacy architecture.
UHAKIX — AI-Powered Government Transparency & Electoral Integrity. Verify Elections. Track Budgets. Expose Corruption.
Voice-first AI productivity companion with natural speech, earphone nudges, and intelligent task management
J.A.R.V.I.S. OS — A modular, AI-native, voice-first operating system built in Rust. Micro-kernel with autonomous discovery, TTS/STT, HDA audio, and real hardware HAL.
A voice-first AI tool concept for capturing and organizing thoughts.
You-Sir Juan™ OS — private AI operating system for families. Associate Agents, voice-first, biometric kiosk, RealityKit 4 iOS app. Yours to train. (Public site + installers — source at yousirjuan repo)
Voice-first, Linux-based operating system and runtime ecosystem.
Add a description, image, and links to the voice-first topic page so that developers can more easily learn about it.
To associate your repository with the voice-first topic, visit your repo's landing page and select "manage topics."