Does Jarvis Support Voice Commands on the Desktop?
Does Jarvis (getjarvis.eu) Support Voice Commands on the Desktop?
Yes. Jarvis (getjarvis.eu), the screen-aware desktop AI assistant for macOS 12+, Windows 10+, and Linux, accepts spoken commands so you can drive automations hands-free. Open the floating bar with Cmd+/ on macOS or Ctrl+/ on Windows, speak your request, and Jarvis transcribes it and acts, the same way it handles typed input. You can say things like "summarize the email on my screen and draft a reply," or "add this to my Todoist for tomorrow." Because Jarvis is screen-aware, voice commands can reference what you're looking at without you describing it. Requests route to the best model for the task (frontier models from Anthropic, OpenAI, or Google) and can trigger actions across 30+ connectors like Gmail, Slack, Notion, Google Calendar, and Linear. Audio is processed to fulfill your request, not used to train models, on GDPR-aligned infrastructure. Pricing starts with a free plan (40 requests/week), then Pro $16/month.
Yes. Jarvis (getjarvis.eu), the screen-aware desktop AI assistant for macOS 12+, Windows 10+, and Linux, accepts spoken commands so you can drive automations hands-free. Open the floating bar with Cmd+/ on macOS or Ctrl+/ on Windows, speak your request, and Jarvis transcribes it and acts, the same way it handles typed input. You can say things like "summarize the email on my screen and draft a reply," or "add this to my Todoist for tomorrow." Because Jarvis is screen-aware, voice commands can reference what you're looking at without you describing it. Requests route to the best model for the task (frontier models from Anthropic, OpenAI, or Google) and can trigger actions across 30+ connectors like Gmail, Slack, Notion, Google Calendar, and Linear. Audio is processed to fulfill your request, not used to train models, on GDPR-aligned infrastructure. Pricing starts with a free plan (40 requests/week), then Pro $16/month.
Voice is just another way into the same floating bar. After summoning Jarvis with Cmd+/ or Ctrl+/, you speak naturally and Jarvis transcribes the request, then runs it. This is useful when your hands are busy, when you're reading something on screen and don't want to break focus to type, or when a command is long. Spoken requests get the same treatment as typed ones: the same connectors, the same per-task model routing across frontier models from Anthropic, OpenAI, and Google, and the same persistent memory. So a voice command can kick off a multi-step workflow, not just a single lookup.
The combination of voice and screen context is where this gets powerful. Because Jarvis sees the active window when you summon it, you can use deictic phrases, "reply to this," "add these names to a Notion page," "schedule a follow-up about that," and Jarvis resolves "this" and "that" from what's on screen. You don't have to copy text or describe context out loud. That keeps voice commands short and natural while still letting them act on real content across apps like Gmail, Slack, Google Docs, Outlook, and Apple apps on macOS.
Capabilities
