The Drive - AI Voice Ordering System

Select Restaurant

Choose a restaurant to start a voice ordering session

System Configuration

Manage audio, filters, and API settings

Current Configuration to Server

These values will be sent when you save

Amplitude Threshold: -

Wait Duration: -

Sample Rate: -

User ID: -

Filter Order: -

High-Pass Cutoff: -

Low-Pass Cutoff: -

Base URL: -

API Key: -

Model API Key: -

Token: -

Voice ID: -

Audio Configuration

Voice detection and streaming settings

Amplitude Threshold Minimum amplitude to trigger streaming

Wait Duration Seconds to continue after silence

sec

Sample Rate Audio sample rate in Hz

Filter Configuration

Butterworth filter noise reduction

Filter Order Order of the Butterworth filter

High-Pass Cutoff Removes low-frequency noise

Low-Pass Cutoff Removes high-frequency noise

Audio Processing (Drive-Thru)

Real-time noise reduction and voice clarity for drive-thru environments

Gain Control

Input Gain Amplify weak microphone signal (1.0 = normal)

1.5x

Output Gain Final volume adjustment (1.0 = normal)

1.2x

Noise Gate

Mutes audio below threshold to cut background noise

Threshold dB level below which audio is muted

-50 dB

Attack Time to open gate (seconds)

sec

Release Time to close gate (seconds)

sec

Voice Filters

High-Pass Filter Remove low rumble (cars, AC, engines)

100 Hz

Low-Pass Filter Remove high-frequency hiss/static

8000 Hz

Compressor

Evens out loud and quiet speech for consistent volume

Threshold dB level to start compressing

-24 dB

Ratio Compression ratio (e.g., 4:1)

4:1

Attack Response time (seconds)

sec

Release Recovery time (seconds)

sec

Audio Level Monitor

-60dB -40dB -20dB 0dB

User Configuration

User identification settings

User ID Unique identifier for the user

API Configuration

API endpoints and authentication keys

Base URL API endpoint base URL

API Key Authentication key for API

Model API Key API key for AI model access

Authentication Token JWT authentication token

Voice ID Unique identifier for voice synthesis