Vocode is an open source Python library for developers building voice AI agents, with a self-hosted telephony server and support for live conversations through a computer's microphone and speakers. It connects speech recognition, an LLM, and speech synthesis in one library. The code uses the MIT license.
Its modular design lets you choose speech providers separately from the language model. That matters if you want to use local speech components for one application and cloud services for another, or compare voices without replacing the rest of your application.
Vocode supports inbound calls to an AI agent and outbound calls managed by an agent. Agents can also dial into Zoom meetings, and a LangChain agent can place an outbound call to a real phone number. Beyond telephony, the library can serve as the voice layer for a personal assistant or an interactive application such as voice-controlled chess. A React SDK is also available.
Speech recognition integrations include Whisper and Whisper.cpp alongside cloud services such as Deepgram, AssemblyAI, Google Cloud, and Microsoft Azure. For generated speech, it supports Coqui and Bark as well as Eleven Labs, Cartesia, AWS Polly, and other providers. Its listed LLM integrations are OpenAI and Anthropic.
Self-hosting the telephony server doesn't make every part of the conversation local. When you choose cloud transcription, LLM, or speech synthesis services, those services process the corresponding audio or text outside your machine.
Claim this page and we'll verify you by hand. Vocode gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Vocode?Promote it
Something wrong or outdated on this page?
20.3KUpdated 1 hour agoMIT
#Human approval#LLM tracing#MCP
Pydantic AI is a Python SDK for developers building AI agents into their own applications. Its main draw is Pydantic validation across agent tools and results, so an agent can return structured data that application code can check and use. The SDK is MIT licensed.
29.8KUpdated 23 hours agoMIT
macOS · Windows · Linux#Code execution#Guardrails#Human approval
26.6KUpdated 1 day agoApache-2.0
Docker#Guardrails#Hugging Face integration#Hybrid search
778Updated 2 days agoMIT
Docker#Human approval#Multilingual#Tool calling
7.2KUpdated 23 hours ago
Docker#Guardrails#LLM tracing#Tool calling
13KUpdated 21 hours agoApache-2.0
Docker#Agent Skills#Hugging Face integration#Knowledge graphs
OpenAI Agents SDK is an open-source Python framework for developers building AI apps that need to use tools, delegate tasks, or work across multiple steps. Its runtime manages agent turns and conversation state while letting developers express workflows in ordinary Python. It uses the MIT license.
Haystack is a Python framework for developers building self-hosted AI agents, document search, and apps that answer questions using their own data. Its modular pipelines let teams control which information reaches a model and inspect how retrieval, memory, tools, and generation contribute to an answer. It's open source under Apache 2.0.
Bolna is a voice AI agent platform for businesses handling customer support, lead qualification, reminders, and recruitment calls. Its focus is Indian languages and accents, including Hindi, Hinglish, Tamil, and Telugu, alongside English. Developers can self-host its MIT-licensed Python orchestration core, while business teams can use a hosted dashboard to build agents without code.
NeMo Guardrails is an open-source Python toolkit for developers who need control over how an AI assistant responds and uses tools. It runs within your application or as a self-hosted server, including in Docker. The library uses the Apache 2.0 license.
txtai is a Python framework for developers building search applications, chat with their data, and AI agents on their own hardware or servers. Its embeddings database combines sparse and dense vector search with graphs and relational data, so the same system can find related content and supply context to language models. It's open source under Apache 2.0.