> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openwhispr.com/llms.txt
> Use this file to discover all available pages before exploring further.

# The voice agent

> Press a key, say what you want done, and the result is typed at your cursor instead of your words.

The voice agent turns speech into an **instruction** rather than text. Press its
hotkey, say what you want, and what appears at your cursor is the result — a
drafted email, a rewritten paragraph, an answer.

The app sums it up as *"Speak a request — your AI agent types the result, not
your words."*

## Setting it up

**1. Give it a hotkey.** Open **Settings**, then **Hotkeys** under **App**, and
set the **Voice Agent Hotkey**. It's empty by default, so until you set one the
only way to reach the agent is by [saying its name](/help/agent/agent-name).

**2. Check it's enabled.** Open **Settings**, choose **Language Models** under
**AI Models**, then the **Voice Agent** tab. **Enable voice agent** is on by
default.

## Using it

Press the hotkey and speak. You don't need to say the agent's name first — the
hotkey already means "this is an instruction". The app's examples:

* *"Translate to Italian: I talk faster than I type"*
* *"Write a short email to my boss telling him I want a promotion, his name is
  Mark"*
* *"What is 5 × 5?"*

The result is typed wherever your cursor is, exactly like dictation — you can
use it inside an email, a document, a chat box.

## Choosing where it runs

On the **Voice Agent** tab you choose the model, independently of the ones used
for transcription and cleanup:

| Mode                   | What it means                                        |
| ---------------------- | ---------------------------------------------------- |
| **OpenWhispr Cloud**   | Managed for you, no API key needed                   |
| **Bring your own key** | OpenAI, Anthropic, Gemini, or Groq with your own key |
| **Local**              | An on-device model — fully private                   |
| **Self-hosted**        | Your own OpenAI-compatible endpoint                  |
| **Enterprise**         | AWS Bedrock, Azure OpenAI, or Google Vertex          |

Cloud and self-hosted modes work without naming a model. The others need one
chosen explicitly, and the agent won't run until you do.

## Its instructions

**Agent prompt**, on the same tab, is the system prompt used when the agent
runs. Leave it empty and a built-in default is used. Set it if you want a
consistent tone or format across everything the agent writes.

## If nothing happens

If the agent can't run — no model chosen in a mode that needs one, or it's
switched off — a dictation started with the voice agent hotkey comes back as
**the plain transcript**, with no cleanup applied. So getting your own raw words
back from that shortcut is the signal that the agent isn't reachable, rather
than that it misunderstood you.

Check, in order: **Enable voice agent** is on, and a model is selected if your
mode requires one.

<Snippet file="still-need-help.mdx" />

## Related

* [Your agent's name](/help/agent/agent-name)
* [The four things your voice can start](/help/agent/voice-modes)
* [The chat agent](/help/agent/chat-agent)
* [Your hotkeys](/help/dictation/hotkeys)