Low-latency, real-time speech-to-speech agents with streaming audio, VAD, and bidirectional WebSockets.
AI Speech Trainer is an AI-powered multi-agent, multimodal public speaking coach that listens to how you speak, watches how you express, and evaluates what you say - helping you become a confident public speaker.
Ramble at your agent by voice. Audit what it heard before it acts.
A low-latency conversational voice agent utilizing OpenAI's Realtime API to handle live speech-to-speech interaction, tool execution, and session management.
A turn-based audio processing pipeline built with OpenAI Agents SDK that processes pre-recorded audio through speech-to-text, agent reasoning, and audio synthesis.
An interactive streaming voice agent built with the OpenAI Agents SDK, featuring live speech detection, turn-taking management, and continuous audio streaming.
Voice agents combine the power of AI language models with speech processing to create natural conversational interfaces. Think of voice agents as AI assistants you can talk to naturally that.
Converts written blog posts and articles into multi-speaker audio podcasts by combining Firecrawl web scraping, GPT-4 summarization, and ElevenLabs voice generation.
An OpenAI SDK powered customer support agent application that delivers voice-powered responses to questions about your knowledge base using OpenAI's GPT-4o and TTS capabilities. The system crawls through documentation websites with...
A voice-first insurance claim intake app that lets a claimant talk naturally while the agent builds a structured claim packet in real time. The UI shows the live conversation, extracted claim facts, operator guidance, missing items, and...
A conversational voice agent system that generates immersive, self-guided audio tours based on the user’s location, areas of interest, and tour duration. Built on a multi-agent architecture using OpenAI Agents SDK, real-time information...
This script demonstrates how to build a voice-enabled Retrieval-Augmented Generation (RAG) system using OpenAI's SDK and Streamlit. The application allows users to upload PDF documents, ask questions, and receive both text and voice...
A generative speech model for daily dialogue.
The open-source AI voice studio. Clone, dictate, create.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
End-to-end realtime stack for connecting humans and AI.
Production ready toolkit to run AI locally.
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready.
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents.
Voice AI SDK is a reusable Android library that gives any app a full voice-driven AI conversation pipeline in minutes. Voice Assistant + Android Voide AI + SDK + MVVM + Kotlin.
The Self-Coding System for Your App — Alan AI SDK for Web.
Open-source voice-AI SDK. The Vapi/Retell alternative for builders who want to own the stack. Give your AI agent a phone number in 4 lines — Python and TypeScript, MIT licensed, Twilio, Telnyx, and Plivo.
EVA OS — A real-time multimodal AIOS for next-generation hardware, enabling your devices being “alive” and as intelligent as a real brain.
This app can now use Android, just like a human.
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
