AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Voice / Speech/
py-xiaozhi
py-xiaozhi logo

py-xiaozhi

Active·★ 3.5k·MIT·Updated 2026-09-11

py-xiaozhi is a Python implementation of the Xiaozhi voice client, intended for learning through code and for experiencing Xiaozhi's voice features without the hardware. It is ported from the xiaozhi-esp32 project, and the README is in Chinese with an English version.

Features include voice interaction, visual multimodal understanding, configurable wake words using offline Sherpa-ONNX recognition, and an MCP tool ecosystem: system control, schedule management, countdown timers, online music playback, 12306 train ticket queries, web search through Bing, a recipe library, Amap maps, a traditional Bazi fortune-telling tool and a camera tool. It also has IoT device management, audio processing (Opus, resampling, voice activity detection, WebRTC echo cancellation), a PyQt5 GUI, a command-line mode for embedded or headless use, a system tray and WSS encrypted audio transport. It needs Python 3.9 to 3.12, a microphone and speakers and a stable internet connection, with at least 4 GB of RAM recommended 8 GB, and optional model downloads for wake words. The README asks users to reinstall pip dependencies after each update. It is MIT licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-25.

License
MIT
Latest release
v2.1.2 · 2026-09-11
Last commit
2026-09-11
Contributors
24
Forks
743
Open issues and PRs
8
First published
2025-02-15

Source: GitHub, npm and PyPI public APIs.

#AI Voice Assistant#Python#Multi-modal AI#IoT Integration#Speech Processing#Coding
$ Install
$ pip install -r requirements.txt
↗ Visit site★ GitHub
01

Features

01AI Voice Interaction
02Visual Multi-modality
03Smart Wake-up
04MCP Tool Ecosystem
05IoT Device Integration
02

Why choose it

+Lets you try Xiaozhi's voice assistant on a computer without ESP32 hardware, with a GUI or a command-line mode.
+Offline wake-word detection with Sherpa-ONNX, plus echo cancellation, voice activity detection and encrypted WSS audio.
+A broad set of MCP tools (schedule, timers, music, train tickets, web search, maps and more) and IoT device management.
+Cross-platform, MIT licensed, with documentation and a video tutorial.
03

Trade-offs

!It depends on the Xiaozhi service for AI features, so it is a client rather than a self-contained assistant.
!It needs Python 3.9 to 3.12, working audio devices, an internet connection and, for wake words, a separate model download.
!The README tells users to reinstall pip dependencies after every update and is written mainly in Chinese.
05

Maintenance check

ActiveChecked: 2026-10-25
Last commit
2026-09-11
Commits, last 90 days
5
Releases, last 90 days
1
Latest release
v2.1.2 (2026-09-11)
Open issues
8
Recent issues with at least one comment
6/10
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 1, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #317 [Improvement] py-xiaozhi should be only a library4 comments · 2026-08-07
  • #316 Looking for Open-Source Infrastructure Sponsorship: Storage, CDN or Server1 comments · 2026-07-28
  • #325 [Security] TLS 证书验证在全部传输层被禁用（WebSocket / OTA / 激活 / MQTT），与文档中 "certificate verification" 的说明不符0 comments · 2026-10-09
  • #323 Optional consent-based memory for recurring voice sessions0 comments · 2026-09-28
  • #322 Feature Suggestion: Optional token metering & paid API key support via `neuforge-pay`0 comments · 2026-09-12

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You want to try the Xiaozhi voice assistant on a computer without ESP32 hardware.
  • You want offline wake words with Sherpa-ONNX, echo cancellation and a GUI or command-line mode.
  • You want ready MCP tools such as schedules, timers, music, train tickets, web search and maps.
Look elsewhere if
  • You want a self-contained assistant: AI features depend on the Xiaozhi service.
  • You cannot use Python 3.9 to 3.12, working audio devices and an internet connection.
  • You want to self-host the backend: that is the server projects' job.
06

How it differs

xiaozhi-esp32-server logovs xiaozhi-esp32-server★ 11.1k

xiaozhi-esp32-server is a backend for Xiaozhi devices. py-xiaozhi is a client that plays the device's role on a computer.

Full comparison →
07

Compatibility

Windows
Native Support
Verified via docs
macOS
Native Support
Verified via docs
Linux
Native Support
Verified via docs
08

Quick start

1
$ pip install -r requirements.txt
09

Use cases

↳Learning Python AI voice client development
↳Experiencing Xiaozhi AI voice features on PC
↳Remote or automated smart device control
10

Alternatives

⚡Top VS:
VSxiaozhi-esp32-server★11.1k→VSChatTTS★40.0k→VSlangchain4j-aideepin★1.4k→VSOpen Interpreter★68.7k→
xiaozhi-esp32-server logo
xiaozhi-esp32-server★ 11.1k
本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
VSCompare→
ChatTTS logo
ChatTTS★ 40.0k
A generative speech model for daily dialogue.
VSCompare→
langchain4j-aideepin logo
langchain4j-aideepin★ 1.4k
基于AI的工作效率提升工具（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | Ai-based productivity tools (Chat,Draw,RAG,Workflow,MCP marketplace, ASR,TTS, Long-term memory etc)
VSCompare→
Open Interpreter logo
Open Interpreter★ 68.7k
A coding agent for the terminal, optimized for low-cost and open models. Forked from OpenAI's Codex, it can emulate other agent harnesses and runs commands in a native sandbox.
VSCompare→
Microsoft AutoGen logo
Microsoft AutoGen★ 61.6k
A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.
VSCompare→
CrewAI logo
CrewAI★ 60.2k
Framework for orchestrating role-playing, autonomous AI agents. By working together, your Crew can tackle complex tasks.
VSCompare→
BettaFish logo
BettaFish★ 42.5k
Multi-agent opinion analysis assistant. Breaks information bubbles and predicts trends.
VSCompare→
GPT Researcher logo
GPT Researcher★ 30.3k
An autonomous agent that conducts deep research on any data using any LLM provider, producing detailed reports with citations from web and local sources.
VSCompare→
See all alternatives →

Featured in these lists

  • Best Open-Source Voice Assistants and Speech Tools

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
huangjunsen0406 /
py-xiaozhi
↗

Python desktop client for the Xiaozhi voice assistant, with wake word and MCP tools

3.5k743MIT
Last commit1mo ago
StatusActive
CategoryVoice / Speech
Contributors24
Latest releasev2.1.2
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.