Added speech support from agent running in docker in linux

[rame0]

Background

Speech does not work when running on Docker container.

Changes

• An additional Dockerfile (speech_linux.Dockerfile) has been added to provide support for audio output from a container.
• Changed docker-compose.yml to allow for a custom Dockerfile.
• Added volumes to docker-compose.yml that bind the host sound to the container.

Documentation

Added comments to docker-compose.yml

Test Plan

Tested on Manjaro Linux.

PR Quality Checklist

• [x] My pull request is atomic and focuses on a single change.
• [x] I have thoroughly tested my changes with multiple different prompts.
• [x] I have considered potential risks and mitigations for my changes.
• [x] I have documented my changes clearly and comprehensively.
• [x] I have not snuck in any "extra" small tweaks changes

No tests added because the actual code doesn't change.

[github-actions[bot]]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[k-boikov]

I think we should find a better way to manage this than uncommenting Dockerfile lines.

[rame0]

I think we should find a better way to manage this than uncommenting Dockerfile lines.

Agree, but that what I come up with so far. Will try to find better solution.

The reasons of uncommenting in docker-compose.yml right now is

1. to have different Dokckerfiles, because, I think (can't test) this sound solution will not work on Windows
2. to still have Dockerfile without sound, because it creates smaller image

The solution might be: creating second service (let's say auto-gpt-speek) in docker-compose.yml with settings for sound. And run like that:

docker-compose run --build --rm auto-gpt-speek

[p-i-]

This is a mass message from the AutoGPT core team. Our apologies for the ongoing delay in processing PRs. This is because we are re-architecting the AutoGPT core!

For more details (and for infor on joining our Discord), please refer to: https://github.com/Significant-Gravitas/Auto-GPT/wiki/Architecting

[ntindle]

Take a look at: https://docs.docker.com/compose/profiles/

[Pwuts]

Since there has been no activity in the past 2+ months, I'm closing this as stale. Feel free to bump, comment here or ping me (on discord) if you want to fix up this PR or if you want to discuss further.