智谱清言 for Home Assistant (Marketplace integration)

Installs: 60 sharing analytics
GitHub stars: 75
Connection: Uses the vendor's cloud
Upkeep: Updated in the last 6 months
Version: v2026.09.0, September 27, 2026
Kind: Marketplace integration
Needs: Needs the Marketplace (HACS on 2026.10 and older)
Domain: zhipuai
Source: github.com/Desmond-Dong/zhipuai
Issues: Report an issue

Independent directory, made by the developer of Vulpo. Not affiliated with Home Assistant or the Open Home Foundation.

Screenshots From the README of Desmond-Dong/zhipuai.

About

智谱清言(ZhipuAI) is a custom integration that connects Home Assistant to the Zhipu cloud language models. It adds a conversation agent for Assist that streams replies, can call Home Assistant tools to control and query devices, and switches to a vision model when a message carries an image. An AI Task part produces structured JSON data and generates images with the CogView models. Speech synthesis and speech transcription are also included, each as an entity and as a service, with several voices and adjustable speed and volume for speech output. Separate services handle image analysis and image generation, and an experimental option writes automations from natural language descriptions. Each part has its own settings, with a recommended mode and an advanced mode. Setup is done in the UI with a Zhipu API key.

Automatic summary of the README and code of Desmond-Dong/zhipuai. Something wrong, or are you the maintainer and want your own text here? Get in touch

Supports

Uses the vendor's cloud Needs an internet connection and an account with the vendor.
From the Marketplace Installed through the Marketplace, formerly HACS.
Actively maintained Its author released or pushed a change in the last six months.

Setting it up

Install it from the Marketplace and restart Home Assistant, then add it under Settings, Devices and services.

Connect to ZhipuAI

API Key

Texts from the code of Desmond-Dong/zhipuai.

Actions

Generate ImageGenerate image using ZhipuAI CogView modelFields: Prompt, Image Size, Model
Analyze ImageAnalyze image content using ZhipuAIFields: Image File, Image Entity, Analysis Prompt, Model, Temperature, Max Tokens, Stream Output
TTS Speech SynthesisConvert text to speech using ZhipuAIFields: Text, Voice Type, Speed, Volume, Response Format, Encode Format, Stream Output, Media Player
STT Speech TranscriptionConvert speech to text using ZhipuAIFields: Audio File, STT Model, Temperature Parameter, Language, Stream Output