# AI use cases for Jarvis Assistant Vocal (sosoj92/jarvis-assistant-vocal) Repo: [sosoj92/jarvis-assistant-vocal](https://github.com/sosoj92/jarvis-assistant-vocal) | Use cases: 4 | Page: https://dedupedai.com/use-cases/sosoj92-jarvis-assistant-vocal/ Jarvis is a French voice assistant that runs on a Windows PC, using Claude, OpenAI or a local Ollama model with tools for smart home, OBS, the browser, calls and an MCP server. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Control lights, OBS and PC apps by voice on Windows: https://dedupedai.com/use-cases/sosoj92-jarvis-assistant-vocal/voice-control-lights-obs-pc/ - Run the voice assistant fully offline with Ollama: https://dedupedai.com/use-cases/sosoj92-jarvis-assistant-vocal/run-jarvis-fully-offline-local/ - Expose Jarvis home and PC tools to an MCP client: https://dedupedai.com/use-cases/sosoj92-jarvis-assistant-vocal/expose-home-pc-tools-via-mcp/ - Generate a daily A4 personal briefing PDF: https://dedupedai.com/use-cases/sosoj92-jarvis-assistant-vocal/daily-personal-briefing-pdf/ ## How to control lights, OBS and PC apps by voice on Windows with Jarvis Assistant Vocal Repo: [sosoj92/jarvis-assistant-vocal](https://github.com/sosoj92/jarvis-assistant-vocal) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Install Jarvis on a Windows 11 PC and use the wake word to run lights, OBS and app commands. **Who it is for:** A streamer or home user on Windows 11 who wants hands-free control of Hue lights, OBS and PC apps while working at the desk. **The problem:** Switching between lights, streaming software and apps by hand breaks focus, especially during a live session. **The outcome:** Jarvis answers to 'Hey Jarvis', switches Hue lights and OBS scenes, and opens apps, with spoken replies. ### Steps 1. Download the repository and double-click `INSTALLER_JARVIS.bat` in the project folder. 2. Wait for the installer to finish, including the setup assistant (`scripts/setup.py`). Your existing `config.yaml` is kept. 3. Launch the assistant with `lancer_jarvis.bat`. 4. Say 'Hey Jarvis' and try a light command, then an OBS command such as starting or stopping a recording. 5. Check the spoken reply and confirm the Hue light or OBS state changed. ### Prompt to paste into your agent ```text In the sosoj92/jarvis-assistant-vocal repo on Windows 11, set up Jarvis and configure the tool for . Expected output: the assistant responds to a spoken command and the target changes state. Verify the change in the Hue app or OBS before reporting success. ``` ### Caveat The README says most integrations are optional and disable themselves when not configured, so only the tools you set up will respond. Risk, credentials: Cloud mode needs an OpenAI or Anthropic key in the config, so keep config.yaml out of shared folders and version control. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sosoj92-jarvis-assistant-vocal/voice-control-lights-obs-pc/ ## How to run the voice assistant fully offline with Ollama with Jarvis Assistant Vocal Repo: [sosoj92/jarvis-assistant-vocal](https://github.com/sosoj92/jarvis-assistant-vocal) | Difficulty: Advanced | Time: 2 hours | Basis: From the README Use the local mode with Ollama and a local voice so no API or usage cost is needed. **Who it is for:** A privacy-minded user or a person with no cloud budget who wants a voice assistant that works without internet after setup. **The problem:** Cloud assistants send voice and requests to external providers and charge per use, which some users want to avoid. **The outcome:** Jarvis runs in local mode with Ollama (qwen3.5:4b) and Piper or Kokoro voice, with no API calls or usage fees. ### Steps 1. Run the install steps from the README: `uv sync`, then `uv run play`. 2. Run `python scripts/doctor.py` to check your hardware and see which local model it recommends for your VRAM. 3. Set the mode to local in `config.yaml` (`mode: local`), or say 'passe en local' once Jarvis is running. 4. Choose Piper, Kokoro or Windows as the voice engine. 5. Ask a simple domotique or PC question and check that the answer comes from the local model. ### Prompt to paste into your agent ```text In the sosoj92/jarvis-assistant-vocal repo, configure local mode with Ollama and a local voice on this machine. Expected output: `python scripts/doctor.py` reports a recommended local model and Jarvis answers a spoken request with no cloud call. Verify that the mode shows as local before reporting success. ``` ### Caveat The README warns that local 7B models handle domotique and PC tools well but browser and reservation features still work best with a cloud model. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sosoj92-jarvis-assistant-vocal/run-jarvis-fully-offline-local/ ## How to expose Jarvis home and PC tools to an MCP client with Jarvis Assistant Vocal Repo: [sosoj92/jarvis-assistant-vocal](https://github.com/sosoj92/jarvis-assistant-vocal) | Difficulty: Advanced | Time: 1 hour | Basis: From the README Start the MCP server so an MCP client such as Claude Desktop can use Jarvis home and PC tools. **Who it is for:** A developer or power user who already uses an MCP client and wants it to control Jarvis lights and PC tools. **The problem:** An AI client has no access to the home or PC controls on the local machine, so it cannot act on them. **The outcome:** An MCP client lists and calls the Jarvis domotique and PC tools through the local MCP server. ### Steps 1. Install and start Jarvis with `uv sync` and `uv run play` first, so the tools are configured. 2. Find the MCP server entry point in the repository docs or source, since the README does not give the start command. (inferred, check the README) 3. Add the MCP server to your client's configuration as a local stdio server. (inferred, check the README) 4. Restart the MCP client and check that the Jarvis tools appear in its tool list. 5. Ask the client to run one safe tool, such as reading a light state, and confirm the result. ### Prompt to paste into your agent ```text In the sosoj92/jarvis-assistant-vocal repo, find the MCP server start command and register it with . Expected output: the client lists the Jarvis home and PC tools and one read-only call returns a result. Verify the tool list before reporting success. ``` ### Caveat The README names the MCP server and the clients it supports but does not give the exact start command or client config, so those steps must be checked in the source. Risk, remote script: An MCP client that can call PC tools may run actions on the machine, so start with read-only tools and check the N1/N2/N3 levels before granting write access. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sosoj92-jarvis-assistant-vocal/expose-home-pc-tools-via-mcp/ ## How to generate a daily A4 personal briefing PDF with Jarvis Assistant Vocal Repo: [sosoj92/jarvis-assistant-vocal](https://github.com/sosoj92/jarvis-assistant-vocal) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Build a monochrome A4 daily briefing from a validated JSON file and print it on a schedule. **Who it is for:** A person who wants a printed morning briefing with news, agenda and priorities, produced automatically from their own data. **The problem:** Gathering agenda, news and priorities each morning takes time and is easy to skip. **The outcome:** A preview HTML and an A4 PDF briefing, printed at a fixed time or at the first PC start of the day. ### Steps 1. Install and start Jarvis with `uv sync` and `uv run play`. 2. Read the Signal Matin guide in docs/signal_matin.md and prepare the JSON input it expects. 3. Generate the HTML preview and check the layout and density. 4. Choose one automation: a fixed print time on a machine that stays on 24 hours, or the first daily brief at PC startup. 5. Check the PDF output and confirm the automation does not print twice on a restart. ### Prompt to paste into your agent ```text In the sosoj92/jarvis-assistant-vocal repo, follow docs/signal_matin.md to build a daily briefing from . Expected output: an HTML preview and an A4 PDF file. Verify the PDF opens and contains the agenda and sourced news before reporting success. ``` ### Caveat The README does not state the exact JSON schema or generation command, so the Signal Matin guide must be read before the steps are run. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sosoj92-jarvis-assistant-vocal/daily-personal-briefing-pdf/