Multilingual Audio Guides in Ohrid Guide

Overview

The Ohrid Guide mobile application was designed to make exploring the city more accessible and engaging for visitors from around the world. One of its standout features is the AI-powered multilingual audio guide system, which allows users to listen to detailed descriptions of selected landmarks and attractions in their preferred language.

Rather than requiring users to read lengthy descriptions, the application transforms written content into natural-sounding speech, creating a hands-free and more immersive sightseeing experience.

The Challenge

Ohrid welcomes visitors from many different countries, making language accessibility an important part of the overall user experience. Maintaining manually recorded audio for every attraction and every supported language would require significant time, cost, and ongoing maintenance whenever content changes.

The challenge was to create a scalable solution that could:

• Support multiple languages.
• Automatically generate audio when new content is added.
• Deliver high-quality speech.
• Continue playback while users navigate the application or lock their device.
• Clearly indicate which places offer audio guides.

The Solution

Hopp Solutions implemented an AI-driven audio guide system using Microsoft Azure AI Speech Services.

Every place page contains a written description available in 10 supported languages. Whenever an administrator creates a new place through the application's administration panel, the system automatically generates an audio version of the description for each available language.

The workflow is fully automated:

1. An administrator creates or updates a place.
2. Azure AI Speech converts each language version into natural speech.
3. Ten audio files are generated automatically.
4. The generated files are stored securely in Azure Blob Storage.
5. The mobile application retrieves the correct audio file based on the language currently selected by the user.

This eliminates manual recording while ensuring that audio content always stays synchronized with the latest descriptions.

Background Audio Experience

To provide a native mobile experience, the application integrates the Capacitor Music Controls plugin.

This allows users to continue listening even when:

• the application is running in the background,
• the phone is locked,
• or the user switches to another application.

The integration also connects with the device's native media controls, displaying:

• the name of the current place,
• the Ohrid Guide application icon,
• playback controls such as Play, Pause, Next, and Previous.

This creates an experience similar to popular music and podcast applications while users continue exploring the city.

Improving Discoverability

To make the feature easier to discover, an Audio Guide indicator was introduced on every place card throughout the application.

Instead of opening each location individually, users can immediately identify which attractions include an audio guide.

Since audio guides are available only for selected categories of places, this visual indicator helps users quickly find locations that support the feature and plan their visits accordingly.

Technology Stack

Key Benefits

• Fully automated audio generation for every newly added place.
• Support for 10 languages with synchronized spoken and written content.
• Scalable architecture that requires no manual audio recording.
• Cloud-based storage with Azure Blob Storage for reliable media delivery.
• Native background playback through device media controls.
• Improved accessibility for users who prefer listening instead of reading.
• Enhanced discoverability with visual indicators highlighting locations that offer audio guides.

Results

The AI-powered audio guide system transforms static place descriptions into an interactive travel companion. By combining Azure AI Speech, cloud storage, and native mobile capabilities, Ohrid Guide delivers a multilingual experience that is both scalable for administrators and intuitive for visitors.

The result is a modern tourism application that makes discovering Ohrid more accessible, engaging, and convenient—allowing travelers to enjoy informative audio guides in their preferred language while freely exploring the city.