diff --git a/deploy_voice_feature.sh b/deploy_voice_feature.sh
new file mode 100644
index 0000000..35bea66
--- /dev/null
+++ b/deploy_voice_feature.sh
@@ -0,0 +1,31 @@
+#!/bin/bash
+
+# Update and install necessary dependencies
+sudo apt-get update
+sudo apt-get install -y python3-pip python3-venv ffmpeg
+
+# Create a virtual environment
+python3 -m venv venv
+source venv/bin/activate
+
+# Install required Python packages
+pip install poetry
+
+# Clone the repository if not already cloned
+if [ ! -d "01" ]; then
+  git clone https://github.com/OpenInterpreter/01.git
+fi
+
+cd 01/software
+
+# Install project dependencies
+poetry install
+
+# Set up environment variables for the voice feature
+echo "export OPENAI_API_KEY='your_openai_api_key'" >> ~/.bashrc
+echo "export ELEVENLABS_API_KEY='your_elevenlabs_api_key'" >> ~/.bashrc
+echo "export DEEPGRAM_API_KEY='your_deepgram_api_key'" >> ~/.bashrc
+source ~/.bashrc
+
+# Start the server with the voice feature enabled
+poetry run 01 --server light --expose --qr
diff --git a/docs/server/configure.mdx b/docs/server/configure.mdx
index e40efd6..4674866 100644
--- a/docs/server/configure.mdx
+++ b/docs/server/configure.mdx
@@ -141,3 +141,19 @@ interpreter.tts = "coqui"
   introducing all-local functionality for the Livekit server as soon as
   possible.
 </Note>
+
+### Deploy and Configure Voice Feature in GCP VM
+
+To deploy and configure the voice feature in a GCP VM where Open Interpreter is already installed, you can use the provided `deploy_voice_feature.sh` script. This script automates the entire process, including installing necessary dependencies, setting up environment variables, and starting the server with the voice feature enabled.
+
+1. Download the `deploy_voice_feature.sh` script to your GCP VM.
+2. Make the script executable:
+   ```bash
+   chmod +x deploy_voice_feature.sh
+   ```
+3. Run the script:
+   ```bash
+   ./deploy_voice_feature.sh
+   ```
+
+The script will handle the installation of dependencies, configuration of environment variables, and starting the server with the voice feature enabled using the OpenAI Realtime Voice API.