Show HN: GPT Home, A Home Assistant Built on the Raspberry Pi via the OpenAI API
1–9 of 9 posts
Re: Show HN: GPT Home, A Home Assistant Built on the Raspberry Pi via the OpenAI API
#2ChatGPT at home! Basically a better Google Nest Hub or Amazon Alexa home assistant. Built on the Raspberry Pi using the OpenAI API. Fully customizable with a React frontend accessible from either the Pi's local IP address or gpt-home.local if your network supports mDNS.
Re: Show HN: GPT Home, A Home Assistant Built on the Raspberry Pi via the OpenAI API
#3Neat. Any estimation on the API usage cost?
Re: Show HN: GPT Home, A Home Assistant Built on the Raspberry Pi via the OpenAI API
#4Awesome work! Would love to see a video demo, mainly to see how the speech sounds, delays, and general answers.
This is the perfect project for HN - great readme/setup tutorial too.
Re: Show HN: GPT Home, A Home Assistant Built on the Raspberry Pi via the OpenAI API
#5Can this Assistant actually do something? Or just answer questions? I personally don’t use home assistants for answering questions but for switching on lights or outlets.
Re: Show HN: GPT Home, A Home Assistant Built on the Raspberry Pi via the OpenAI API
#6Can this Assistant actually do something? Or just answer questions? I personally don’t use home assistants for answering questions but for switching on lights or outlets.
Yeah It integrates with Philips Hue, Spotify, and OpenWeatherMap at the moment. The loop parses the recognized text with regex to see what sort of action is being requested and if it is not a predefined action it queries openai and speaks the response.
Re: Show HN: GPT Home, A Home Assistant Built on the Raspberry Pi via the OpenAI API
#7Awesome work! Would love to see a video demo, mainly to see how the speech sounds, delays, and general answers. This is the perfect project for HN - great readme/setup tutorial too.
Re: Show HN: GPT Home, A Home Assistant Built on the Raspberry Pi via the OpenAI API
#8Neat. Any estimation on the API usage cost?
Basically nothing especially if you use cheaper models and set the max token limit in `settings.json`. GPT-4 is $30.00 / 1M tokens for input and $60.00 / 1M tokens for output. For English text, 1 token is approximately 4 characters or 0.75 words. As a point of reference, the collected works of Shakespeare are about 900,000 words or 1.2M tokens. See https://openai.com/api/pricing and https://platform.openai.com/settings/organization/limits for limits.