Open-Source Real-Time Voice Agent Frameworks
Frameworks like Pipecat and LiveKit Agents for building voice agents that hold a spoken conversation in real time.
A Python AI agent framework that supports local gpt-oss through Ollama, tool calling and sandbox workspaces. Open source under MIT.
30.7KUpdated 3 days agoMIT
macOS · Windows · Linux#Code execution#Guardrails#Human approval
OpenAI Agents SDK is a Python framework for developers building tool-using agents with local models or cloud APIs. It supports gpt-oss through Ollama, with LM Studio also documented as a local model option. OpenAI models use the remote Responses API by default and require an API key, even when the agent runtime and workspace run on your machine.
Agent FrameworksLLM Libraries and SDKsVoice Agent Frameworks+0
A self-hosted voice AI platform builds inbound and outbound calling agents with visual workflows, your own AI providers, and telephony integrations.
6.1KUpdated 2 days agoBSD-2-Clause
Docker · Web#MCP#Tool calling#Visual workflows
Dograh is an open source voice AI platform for teams building agents that answer or place phone calls. It's a self-hosted alternative to Vapi and Retell, with control over conversation flows and a choice of AI providers.
AI Workflow AutomationMCP Servers and Agent SkillsVoice Agent Frameworks+0
An open-source voice assistant platform for Linux and Raspberry Pi, with offline speech plugins and connections to local OpenAI-compatible LLM servers.
302Updated 2 weeks agoApache-2.0
Linux · Docker#OpenAI-compatible API#Wake word detection#Works offline
OpenVoiceOS is a voice assistant platform for people building smart speakers or adding voice control to their own devices. Its core is a fork of MycroftAI/mycroft-core, and most classic Mycroft skills remain compatible.
Edge and Embedded AISmart Home AIVoice Agent FrameworksVoice Assistants+0
An open-source AI agent framework routes conversations across specialized agents, with Python and TypeScript runtimes and on-device Swift orchestration.
7.8KUpdated 1 month agoApache-2.0
macOS · iOS#LLM tracing#MCP#Multi-agent workflows
Agent Squad is a framework for developers building assistants that divide work among specialized AI agents. It handles agent selection and conversation context so users can switch topics without starting a separate chat.
Agent FrameworksVoice Agent Frameworks+0
A Python library connects live audio and video to your code through WebRTC or WebSockets, with voice turn taking and Gradio or FastAPI integration.
4.6KUpdated 3 weeks agoMIT
Web#Streaming inference#Voice activity detection
FastRTC is a Python library for developers building voice assistants, webcam AI apps, and other interactive audio or video tools. It connects live media streams to Python functions so developers can focus on how their application responds.
LLM Libraries and SDKsVoice Agent Frameworks+0
An open-source Python framework for self-hosted voice and video agents under BSD 2-Clause. Speech and model processing use the services you choose.
17.2KUpdated 20 hours agoBSD-2-Clause
#LLM tracing#Multi-agent workflows#Multimodal input
Pipecat is an open-source Python framework for developers who want to run voice and video agent applications locally or on their own servers. It hosts the conversation pipeline, while speech and model processing depend on the services you choose. Integrations such as Soniox, OpenAI and Cartesia send the relevant requests to those providers.
Agent FrameworksVoice Agent Frameworks+0
An open-source voice AI agent framework for Python and Node.js, with self-hosted deployment, phone integration and conversation interruption handling.
15.2KUpdated 19 hours agoApache-2.0
#MCP#Multi-agent workflows#Multimodal input
LiveKit Agents is a framework for developers building voice assistants, phone agents and applications that combine speech, video and text. Python and Node.js agents interact with users through LiveKit rooms connected to web, mobile or telephone clients.
Agent FrameworksVoice Agent Frameworks+0
An on-device voice AI toolkit that combines speech recognition, intent recognition and text to speech across desktop, mobile and browser applications.
11.5KUpdated 1 week ago
macOS · Windows · Linux · iOS · Android · Web#Multilingual#Streaming inference
Moonshine is an on-device AI toolkit for developers building voice agents and spoken interfaces. Voice processing runs on the device without an account or API keys.
On-Device and In-Browser AISpeech-to-Text and TranscriptionSpeech-to-Text ModelsText-to-Speech and AudiobooksVoice Agent Frameworks+0
A local voice AI model and dialogue framework that listens while speaking, with MLX support for Mac and iPhone and self-hosted server backends.
11.5KUpdated 6 months agoApache-2.0
macOS · iOS · Web#Hugging Face integration#MLX#Quantization
Moshi is a voice AI model and dialogue framework for researchers and developers building spoken applications. It processes speech directly and can listen while it speaks, including information such as emotion and non-verbal cues.
Inference Servers and ClustersOn-Device and In-Browser AIOpen ModelsVoice Agent FrameworksVoice Assistants+0
A voice AI agent platform with a self-hosted MIT-licensed core and hosted tools for inbound and outbound calls in Indian languages.
822Updated 2 days agoMIT
Docker#Human approval#Multilingual#Tool calling
Bolna builds voice AI agents for businesses handling support, sales and recruitment calls. It focuses on Indian languages and accents, including Hindi, Hinglish, Tamil and Telugu, alongside English.
Voice Agent Frameworks+0
An open source Python AI agent SDK with validated outputs, Ollama support and an optional self-hosted model gateway, licensed under MIT.
21.2KUpdated 22 hours agoMIT
#Human approval#LLM tracing#MCP
Pydantic AI is a Python SDK for developers building agents into their applications. It uses Pydantic validation to give application code structured results and check the arguments agents pass to tools.
Agent FrameworksLLM Gateways and RoutersLLM Libraries and SDKsVoice Agent Frameworks+0
An Apache-licensed Python framework for self-hosted text and voice assistants, with NLU and dialogue management, now in maintenance mode.
21.4KUpdated 11 months agoApache-2.0
Web#Guardrails#LLM tracing#MCP
Rasa Open Source is a Python framework for developers building text and voice assistants on their own servers. It provides natural-language understanding, dialogue management and integrations with messaging channels.
Agent FrameworksLLM Evaluation and TestingLLM Observability and TracingVoice Agent FrameworksWebsite and Support Chatbots+0
A self-hosted voice AI framework with RTC and WebSocket support and Docker deployment; its default example uses Agora, OpenAI and Deepgram services.
11.2KUpdated 2 days ago
Docker · Web#Multimodal input#Voice activity detection
TEN Framework is a self-hosted framework for developers building voice agents and multimodal conversational applications. Its default assistant example depends on external services even when the application runs on your hardware.
Agent FrameworksVoice Agent FrameworksVoice Assistants+0
A voice assistant protocol connects Home Assistant to speech and wake word services on a trusted network, with an MIT-licensed Python implementation.
415Updated 5 days agoMIT
#Home Assistant integration#Voice activity detection
Wyoming Protocol connects Home Assistant with separate voice services. It's for developers and people assembling a voice assistant who want to choose their own transcription, speech synthesis, and wake word components. Connections have no authentication or encryption, so it requires a trusted network.
Smart Home AIVoice Agent Frameworks+0
LogotyperGot an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your project
