#voice-ai Repositories
Discover 37 active open source GitHub repositories tagged with #voice-ai, accumulating 272,958 total stars (averaging 7,377 stars per project). Leading this topic is debpalash/VoiceStudio with 115,753 stars.
38 repositories total
VoiceStudio is the open-source, fully local alternative to ElevenLabs โ voice cloning, voice design, video dubbing, dictation, transcription, and audiobook creation in 646 languages.
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
Quickly build text, voice, and video agents. A fast, Go-based agent backend with SDKs for every language. Sensible defaults for search, knowledge, skills, telephony, sandboxes, memory, and persistence. Sovereign AI. Take control of your AI.
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.
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
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
Formerly Better Chatbot. Navigator is an open-source AI workspace for agents, MCP and workflow automation.
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 โ Python and TypeScript, MIT licensed, Twilio, Telnyx, and Plivo.
JARVIS โ a voice assistant for Claude Code. Talk to your Mac and he brainstorms a project with you, builds it, and tells you out loud when a Claude Code session needs you. macOS, on your Claude subscription, no API key.
The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.
Vui Nano โ a small, context-aware text-to-speech model trained on real conversations. 219M active parameters (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Includes a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.
Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.
Self-hosted, API-first AI call center: AI talks, code controls the call. AI agents answer every call; humans can take over without dropping it. Runs on FreeSWITCH with your SIP trunk and a real-time model (OpenAI, Grok, Qwen, Doubao, or any compatible gateway).
TypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors, and self-building designs
Multi-modal voice agent for your AI agents. Talk with Claude Code, Codex, and others by voice: answer their prompts, give instructions, ask what they did. Or just nod.
Enables organizations to create and deploy customizable AI agents with support for multiple LLM providers, real-time chat, voice, document training, analytics, user management, SSO authentication, and embeddable widgets. Built with React 19, Redux Toolkit, Radix UI, and Tailwind CSS.
The Self-Coding System for Your App โ Alan AI SDK for React Native
World's first open-source real-time endโtoโend spoken dialogue model with personalized voice cloning.
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, costs pennies per call with your own keys. Imports Dialogflow CX.
Study Companion Space ยท A local-first anime-style AI 1-on-1 tutor that feels like a video call (with 6 animated tutors, a synced whiteboard, and FSRS review) | Local-first video-call anime AI tutor with synced board & 6 animated tutors
The spend meter and budget gate for AI voice agents. Meters STT + TTS + LLM + telephony per call, out of the box (Pipecat, LiveKit โ Python & TypeScript). Hard-stops the next turn before it crosses your ceiling. Local, no account, no telemetry. Built by Floe โ cost controls for Voice AI.
Frequently Asked Questions
What is the most popular #voice-ai repository on GitHub?
The top ranked open source #voice-ai project on GitHub is debpalash/VoiceStudio with 115,753 stars. VoiceStudio is the open-source, fully local alternative to ElevenLabs โ voice cloning, voice design, video dubbing, dictation, transcription, and audiobook creation in 646 languages.
Which programming languages are most used in #voice-ai repositories?
Among the top ranked #voice-ai projects on GitHub, the most common programming languages are Python, TypeScript, Go, C++.
How is the #voice-ai repository ranking calculated?
We track 37 active open source repositories tagged with #voice-ai (500+ stars), totaling 272,958 stars with an average of 7,377 stars per repository. Rankings update daily from the GitHub API.