LocalAIVoiceChat
big-AGI
LocalAIVoiceChat | big-AGI | |
---|---|---|
4 | 8 | |
325 | 4,445 | |
- | - | |
7.0 | 10.0 | |
6 days ago | 3 days ago | |
Python | TypeScript | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
LocalAIVoiceChat
-
Show HN: Open-source macOS AI copilot (using vision and voice)
Was following these two projects by someuser on Github which makes similar things possible with Local models. Sending screenshot to openai is expensive , if done every few seconds or minutes.
https://github.com/KoljaB/LocalAIVoiceChat
While the below one uses openai - don't see why it can't be replaced with above project and local mode.
https://github.com/KoljaB/Linguflex
-
ChatGPT Voice Announced (By Greg Brockman)
What a coincidence, was just looking something similar for local models and stumbled up on this, his Repo seems full of TTS/STT projects..
https://github.com/KoljaB/LocalAIVoiceChat
- FLaNK Stack Weekly for 13 November 2023
-
Introducing: a local realtime talkbot
Code: If you're curious, want to chip in, or just want to take a look, here's the link to the Github.
big-AGI
- GPT-4 Turbo with Vision is a step backwards for coding
- LM Studio – Discover, download, and run local LLMs
- ChatGPT Voice Announced (By Greg Brockman)
-
Is there an easy way to use the March 14th model ChatGPT-4 model?
You could run a local copy of big-agi and edit this file to use the dated model.
-
Managing ChatGPT token/character limits tool
As ChatGPT counts tokens for both inputs and output, you'd have to be thoughtful for the input side as well so this is where the tool would come in handy within the same chat session. I don't think it remembers separate chat sessions so yeah without access to history, you'd need to either start a new chat session each time or setup your own ChatGPT instance and use your own OpenAI API token and be billed. For my own ChatGPT instance I use awesome app at https://github.com/enricoros/nextjs-chatgpt-app which has a demo on the readme page too.
-
Make your own ChatGPT UI
nice, maybe you can make the initializing prompts in
https://github.com/enricoros/nextjs-chatgpt-app/blob/main/pa...
transparent to the user and even changeable by them.
What are some alternatives?
llamafile - Distribute and run LLMs with a single file.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
vimGPT - Browse the web with GPT-4V and Vimium
Lobe Chat - LobeChat is a open-source, extensible (Function Calling), high-performance chatbot framework.It supports one-click free deployment of your private ChatGPT/LLM web application.
cucim - cuCIM - RAPIDS GPU-accelerated image processing library
chatgpt-demo - Minimal web UI for ChatGPT.
wubloader
fill - Generative fill in 3D.
wave - Realtime Web Apps and Dashboards for Python and R
chatbot-ui - AI chat for every model.
PyMISP - Python library using the MISP Rest API
ollama-webui - ChatGPT-Style WebUI for LLMs (Formerly Ollama WebUI) [Moved to: https://github.com/open-webui/open-webui]