[HN Gopher] Show HN: Voxos.ai - An Open-Source Desktop Voice Ass...
___________________________________________________________________
Show HN: Voxos.ai - An Open-Source Desktop Voice Assistant
Voxos is an open-source desktop voice assistant that aims to put
Clippy to shame while supporting new desktop workflows powered by
LLMs. Tired of copy and pasting ChatGPT responses between your web
browser and IDE? Does your copilot not quite do what you need it
to do? I invite you to give Voxos a try and maybe even become a
contributor!
Author : Falimonda
Score : 51 points
Date : 2024-01-19 16:04 UTC (6 hours ago)
(HTM) web link (gitlab.com)
(TXT) w3m dump (gitlab.com)
| Falimonda wrote:
| Voxos is an open-source desktop voice assistant that aims to put
| Clippy to shame while supporting new desktop workflows powered by
| LLMs.
|
| Tired of copy and pasting ChatGPT responses between your web
| browser and IDE?
|
| Does your copilot not quite do what you need it to do?
|
| I invite you to give Voxos a try and maybe even become a
| contributor!
| anotherpaulg wrote:
| _Tired of copy and pasting ChatGPT responses between your web
| browser and IDE?_
|
| How does Voxos help avoid copying & pasting code into your IDE?
| I had a look around the code base and don't see any indication
| that it allows GPT to directly edit your source files. But
| maybe I am missing it?
|
| I'm asking because this is a major focus of my open source AI
| coding project aider [0]. I always like to see how other
| projects approach the challenge of letting GPT edit existing
| code. Most recently, aider adopted unified diffs as the GPT 4
| Turbo code editing format [1].
|
| [0] https://github.com/paul-gauthier/aider
|
| [1] https://aider.chat/docs/unified-diffs.html
| Falimonda wrote:
| Hey there. I'd come across aider a few weeks ago - thrilled
| to have your input on this.
|
| You're correct that Voxos in its current form does not
| directly work with the user's file system. I'll admit I chose
| my words carefully in saying that it spares you from copy and
| pasting between ChatGPT and your IDE - not necessarily that
| you won't be copy and pasting any more. I feel like having
| the text response dump to a text editor helps me speed up my
| workflow considerably when contrasted with the ChatGPT UI
| being "read-only" in this sense.
|
| Anyways, I'd been messing around with function calling in an
| earlier version of Voxos and plan on bringing all that work
| into this beta soon. In terms of my approach, I plan on using
| docker to host a network mapped drive on the host machine.
| Then connecting the IDE from the host to the network mapped
| drive. I'm not sure how well that will carry over to the non-
| beta version of Voxos that I envision will come with an
| installer for non-technical users. I haven't put that much
| work into the idea yet.
|
| An alternative was to host all of it in the cloud and simply
| offer a web IDE to a container, then make sure there's
| reliable backup and revert system in place if/when things go
| south. That's heading more towardsa hosted solution though
| and I simply don't have time to support paying customers even
| once Voxos matures to the point I'd liked for a v1.0.
|
| I'll take a closer look at the unified-diffs when I get a
| chance!
| jsheard wrote:
| To be clear, this is an open-source frontend for a not-open-
| source AI provider. It's calling OpenAI behind the scenes.
| eurekin wrote:
| Can it call anything self hosted or ollama?
| Falimonda wrote:
| That's on the roadmap
| htsh wrote:
| Can one enter their own opeanai URL and api-key? (so we can
| use openai-compatible things like openrouter or lm-studio)?
| nullstyle wrote:
| Doesn't look like it: https://gitlab.com/literally-
| useful/voxos/-/blob/dev/voxos/s...
|
| edit: shouldn't be hard to enable though
| Falimonda wrote:
| Yes, you can define your own key in either the .env, CLI
| call on run.sh, or in your environment.
|
| https://gitlab.com/literally-
| useful/voxos/-/blob/dev/.env?re...
| nullstyle wrote:
| That doesn't let me send requests to my local litellm
| instance, though. You have to be able to configure the
| endpoint that requests are sent against as well.
| lxe wrote:
| I think anything compatible with either chat completions or
| completions API should work.
| speedgoose wrote:
| It should be possible using LiteLLM and a patch or a proxy.
|
| https://github.com/BerriAI/litellm
| Falimonda wrote:
| Fair enough. With that said, support for running a local, self-
| hosted, and non-OpenAI cloud-hosted models is in the works.
| thejohnconway wrote:
| I don't mean to be too dismissive, but this would really only be
| interesting if it ran local voice transcription and a local LLM.
| Falimonda wrote:
| Thanks for your feedback. Local and remote self-hosted
| transcription and LLM integration is on the roadmap.
| nickthegreek wrote:
| This should be a Show HN:
| Falimonda wrote:
| Whoops, thanks for the nudge.
| fuddle wrote:
| A demo would be useful.
| iJohnDoe wrote:
| Agreed. Interested in this and would like to see a demo.
|
| Terms like "Recording" make it seem confusing.
|
| Have the responses open in Notepad is confusing in normal work
| flows.
| anotherpaulg wrote:
| _Tired of copy and pasting ChatGPT responses between your web
| browser and IDE?_
|
| How does Voxos help avoid copying & pasting code into your IDE? I
| had a look around the code base and don't see any indication that
| it allows GPT to directly edit your source files. But maybe I am
| missing it?
|
| I'm asking because this is a major focus of my open source AI
| coding project aider [0]. I always like to see how other projects
| approach the challenge of letting GPT edit existing code. Most
| recently, aider adopted unified diffs as the GPT 4 Turbo code
| editing format [1].
|
| [0] https://github.com/paul-gauthier/aider
|
| [1] https://aider.chat/docs/unified-diffs.html
| Falimonda wrote:
| Hey there. I'd come across aider a few weeks ago - thrilled to
| have your input on this.
|
| You're correct that Voxos in its current form does not directly
| work with the user's file system. I'll admit I chose my words
| carefully in saying that it spares you from copy and pasting
| between ChatGPT and your IDE - not necessarily that you won't
| be copy and pasting any more. I feel like having the text
| response dump to a text editor helps me speed up my workflow
| considerably when contrasted with the ChatGPT UI being "read-
| only" in this sense.
|
| Anyways, I'd been messing around with function calling in an
| earlier version of Voxos and plan on bringing all that work
| into this beta soon. In terms of my approach, I plan on using
| docker to host a network mapped drive on the host machine. Then
| connecting the IDE from the host to the network mapped drive.
| I'm not sure how well that will carry over to the non-beta
| version of Voxos that I envision will come with an installer
| for non-technical users. I haven't put that much work into the
| idea yet.
|
| An alternative was to host all of it in the cloud and simply
| offer a web IDE to a container, then make sure there's reliable
| backup and revert system in place if/when things go south.
| That's heading more towardsa hosted solution though and I
| simply don't have time to support paying customers even once
| Voxos matures to the point I'd liked for a v1.0.
|
| I'll take a closer look at the unified-diffs when I get a
| chance!
| anotheryou wrote:
| > Supports the following LLMs: > OpenAI's Completions Models
|
| so not gpt4.5-turbo? that's the chat API after all.
| ianbicking wrote:
| Looking at the code it uses the chat completion API, so I'm
| guessing the description there is wrong
| anotheryou wrote:
| thanks!
| smcleod wrote:
| Seems to be missing Local LLM / offline support and tied to
| openAI.
| bebrws wrote:
| I made a little proof of concept that used whisper cpp and
| ChatGPT to take "command" requests and generate Apple scripts
| which I could then run in OS X
|
| It actually works somewhat well. I think with some more work and
| thought, something like this, could actually be useful.
|
| Just saw this was for linux and Windows only
| robblbobbl wrote:
| I like the idea and support your project. As an enhancement/a
| suggestion you could let the assistant reply back with the voice
| of the user's choice like in the ChatGPT app.
___________________________________________________________________
(page generated 2024-01-19 23:00 UTC)