Voice

Voice in Deska is not a separate dictation box bolted on the side — it is the front door to Ask Deska. A compact center sits at the bottom of the canvas where you can either type a question or hold to talk, and it carries you through the whole exchange: you speak, Deska listens, thinks, and speaks its answer back, all in one place.

It moves through a few clear states so you always know what is happening:

• Listening — a live waveform shows it is hearing you. Press Esc to cancel or Enter to send.
• Thinking — your words have been transcribed and handed to the model.
• Speaking — the reply streams in, with small chips noting any actions Deska took on the canvas and a link to open the full thread.

You can also dictate while composing a typed message — tap the mic, speak, and the transcription drops into the text field for you to edit before sending.

Because voice flows into Ask Deska, speaking is not limited to dictating text — you can ask for work to be done. Say “run the tests” or “what is failing in the build terminal?” and Deska uses what is open on your canvas to answer, or hands the task to a coding agent and reports back. It is the same assistant you reach with Cmd/CtrlT, just driven by your voice.

Start talking with the global shortcut — CmdShiftV on macOS, or CtrlAltV on Windows and Linux. Because it is registered globally, it works even when Deska is in the background, so you can capture a thought without switching windows first.

• Pick your microphone from the input picker if you have more than one.
• Choose a reply language — Auto matches the language you speak, or pin it to English, Spanish, Portuguese, French, German, Italian, Japanese or Chinese.
• Watch your balance — a credits chip shows what you have left as you go.

While you are talking to Deska, a soft, Apple-Intelligence-style glow breathes around the edges of the window and pulses in time with your voice — a gentle, ambient signal that it is listening, without a modal stealing the screen. The glow is designed for Deska’s dark themes and reacts to your microphone level in real time, fading out the moment the exchange ends.

Every dictation is kept. The Voice panel is a timeline of everything you have said, grouped by day, with a word count on each entry. From any entry you can:

• Copy the text to the clipboard.
• Insert it into whatever field currently has focus.
• Delete it when you no longer need it.

For quick reuse without opening the full panel, the mic button also reveals a small flyout of your most recent dictations with the same copy, insert and delete actions.

Transcription runs on Deska’s servers, so there is nothing to set up. It is one of the managed AI features, which means it draws from your monthly credits — voice is inexpensive, costing roughly half a credit per minute of audio. The agent reply, if you ask Deska to do something, is billed like any other AI request, in proportion to its cost.

On a Lifetime license you can add your own Groq API key under Settings → API Keys. Voice then transcribes on your own account and budget instead of spending Deska credits.

The same voice experience travels to the companion app on the web and your phone — tap the mic, speak, and Ask Deska answers, connected back to the machine where your project lives. It is the easiest way to check on a long task when you are away from your desk.