You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: documentation/docs/guides/sessions/in-session-actions.md
+17-10Lines changed: 17 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -237,23 +237,30 @@ Speak to goose directly instead of typing your prompts.
237
237
1. Click the <PanelLeft className="inline" size={16} /> button in the top-left to open the sidebar
238
238
2. Click `Settings` in the sidebar
239
239
3. Click the `Chat` tab
240
-
4. Under `Voice Dictation`, toggle `Enable Voice Dictation` on
241
-
5. Choose between `OpenAI Whisper` or `ElevenLabs` as your dictation provider
242
-
6. Enter your API key for the provider you chose
240
+
4. For `Voice Dictation Provider`, select your provider from the dropdown:
241
+
- Local — On-device transcription using a local whisper model, no API key needed. On first use, you'll be prompted to download the model.
242
+
- [Elevenlabs](https://elevenlabs.io/)
243
+
- [Groq](https://groq.com/)
244
+
- [OpenAI](https://platform.openai.com/api-keys)
245
+
5. If prompted, enter your API key for the provider you chose
243
246
244
247
To use voice dictation:
245
-
1. Return to your chat (click your chat session under `Chat` in the sidebar)
246
-
2. Click the microphone on the right of the chat box and begin speaking
248
+
1. Click your chat session under `Chat` in the sidebar
249
+
2. Click the microphone button on the right of the chat box and begin speaking
250
+
3. To send your message, do one of the following:
251
+
- Say "submit" to send the message and continue recording your next one. To stop recording, click the microphone button.
252
+
- Click the microphone button to stop recording, then click `Send` or press `Enter`. This option allows you to edit the message before sending.
247
253
248
-
The first time you use voice dictation, goose will request access to your microphone. While recording, you'll see a live waveform of your audio in the input field, a timer, and the current size of your recording. Click the microphone button again to finish recording.
254
+
The first time you use voice dictation, goose will request access to your microphone. While recording, you'll see `Listening` and `Transcribing` status indicators. goose transcribes your speech during natural pauses and adds the text to the chat box.
249
255
250
-
**If you don't see the microphone**, check the [models you have configured](/docs/getting-started/providers.md). ElevenLabs can be used as a dictation provider alongside any LLM, but OpenAI Whisper requires that you have an OpenAI model configured in goose, even if using another LLM provider for chat.
256
+
**If you don't see the microphone**, check the [models you have configured](/docs/getting-started/providers.md). For example, using OpenAI as the voice dictation provider requires that you have an OpenAI model configured in goose, even if using another LLM provider for chat.
251
257
252
258
#### Important Notes
253
-
* You can record up to 10 minutes or 25MB of audio
254
-
* The audio is processed by your chosen provider (OpenAI or ElevenLabs)
255
-
* Voice input is appended to any existing text in the text input field, so you can combine typing and speaking your prompts
259
+
* You can record up to 50MB of audio
260
+
* ElevenLabs, Groq, and OpenAI send audio recordings to their servers for processing. The local provider processes audio entirely on your device—no data leaves your computer.
261
+
* Voice input is appended to any existing text in the text input field
256
262
* Recordings are not stored locally after transcription
263
+
* To disable voice dictation, select `Disabled` from the provider dropdown
Copy file name to clipboardExpand all lines: documentation/docs/mcp/developer-mcp.md
+38-17Lines changed: 38 additions & 17 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -152,6 +152,23 @@ curl x POST http://localhost:3000/api/users \
152
152
Would you like me to add any additional features or make other improvements to the setup?
153
153
```
154
154
155
+
## Environment Variables in Shell Commands
156
+
157
+
Shell commands executed by the `shell` tool inherit the environment of the running goose process. This typically includes:
158
+
- System variables like `PATH`, `HOME`, and `USER`
159
+
- Environment variables present in the process that launched goose (for example, your terminal's environment when you start goose from a shell)
160
+
- Session-specific variables injected by goose, such as `AGENT_SESSION_ID` for [session-isolated workflows](/docs/guides/environment-variables#using-session-ids-in-workflows)
161
+
162
+
This enables workflows that depend on environment configuration, such as authenticated CLI operations and build processes.
163
+
164
+
:::info
165
+
goose Desktop or launcher-based starts may use a different environment and may not load your shell startup files.
166
+
:::
167
+
168
+
:::warning Sensitive Information
169
+
Environment variables may contain sensitive values like API keys and tokens (e.g., `GITHUB_TOKEN`, `AWS_ACCESS_KEY_ID`).
170
+
:::
171
+
155
172
## Configuring Access Controls
156
173
157
174
By default, goose can run system commands with your user privileges and edit any accessible file **without your approval**. This is because goose runs in Autonomous permission mode by default and has access to the Developer extension's shell and file editing tools. While this configuration allows goose to work quickly and independently, there's potential for unexpected outcomes. Understanding the available access control features can help you configure goose to match your comfort level and specific needs.
@@ -172,23 +189,6 @@ The Developer extension provides these tools:
172
189
|`screen_capture`| Take screenshots | Debugging UI issues, documenting state | ✅ Low<br />Visual information only |
173
190
|`image_processor`| Process and resize images | Optimizing assets, format conversion | ✅ Low<br />Image manipulation only |
174
191
175
-
### Environment Variables in Shell Commands
176
-
177
-
Shell commands executed by the `shell` tool inherit the environment of the running goose process. This typically includes:
178
-
- System variables like `PATH`, `HOME`, and `USER`
179
-
- Environment variables present in the process that launched goose (for example, your terminal's environment when you start goose from a shell)
180
-
- Session-specific variables injected by goose, such as `AGENT_SESSION_ID` for [session-isolated workflows](/docs/guides/environment-variables#using-session-ids-in-workflows)
181
-
182
-
This enables workflows that depend on environment configuration, such as authenticated CLI operations and build processes.
183
-
184
-
:::info
185
-
goose Desktop or launcher-based starts may use a different environment and may not load your shell startup files.
186
-
:::
187
-
188
-
:::warning Sensitive Information
189
-
Environment variables may contain sensitive values like API keys and tokens (e.g., `GITHUB_TOKEN`, `AWS_ACCESS_KEY_ID`).
190
-
:::
191
-
192
192
### Access Control Features
193
193
194
194
You can layer multiple controls to match your risk tolerance and workflow:
@@ -240,3 +240,24 @@ As you become more comfortable with goose's behavior, you can adjust these setti
240
240
:::info
241
241
Also see the [Security Guide](/docs/guides/security/) for information about using goose safely.
242
242
:::
243
+
244
+
## Additional Resources
245
+
246
+
import ContentCardCarousel from '@site/src/components/ContentCardCarousel';
247
+
248
+
<ContentCardCarousel
249
+
items={[
250
+
{
251
+
type: 'topic',
252
+
title: 'Enhanced Code Editing with AI Models',
253
+
description: 'Use AI models to intelligently apply code changes',
0 commit comments