---
name: "Build streaming voice LLM agents with Vocode"
slug: "build-streaming-voice-llm-agents-with-vocode"
description: "Use Vocode to compose transcription, LLM, speech synthesis, and telephony components into reviewable real-time voice-agent workflows."
github_stars: 3767
verification: "security_reviewed"
source: "https://github.com/vocodedev/vocode-core"
author: "Vocode"
publisher_type: "organization"
category: "Media & Transcription"
framework: "Custom Agents"
tool_ecosystem:
  github_repo: "vocodedev/vocode-core"
  github_stars: 3767
---

# Build streaming voice LLM agents with Vocode

Use Vocode to compose transcription, LLM, speech synthesis, and telephony components into reviewable real-time voice-agent workflows.

## Prerequisites

Python environment with the vocode package; provider credentials for selected transcription, LLM, speech synthesis, and telephony services; optional LangChain integration for agent-triggered outbound calls.

## Installation

Use the upstream install or setup path that matches your environment:
- pip install vocode

Requirements and caveats from upstream:
- [![pypi](https://img.shields.io/pypi/v/vocode.svg)](https://pypi.python.org/pypi/vocode)
- 🗣 [Spin up a conversation with your system audio](https://docs.vocode.dev/open-source/python-quickstart)
- python

Basic usage or getting-started notes:
- asyncio.run(main())

- Source: https://github.com/vocodedev/vocode-core
- Extracted from upstream docs: https://raw.githubusercontent.com/vocodedev/vocode-core/HEAD/README.md

## Documentation

- https://docs.vocode.dev/open-source

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/build-streaming-voice-llm-agents-with-vocode/)