Voicy - Mobile App Development for Educational Toy Company
Challenge
The goal was to develop a complete MVP of a cross-platform mobile app that allows children to listen to stories narrated in their parent's voice, even when the parent is away. The main challenge was to make AI-generated narration sound recognizably like the original speaker while keeping the voice recording process quick and simple.
The solution also had to ensure instant story playback without repeated generation delays, support offline listening, and enable Bluetooth connectivity with a physical mascot. These requirements called for an architecture that combined AI voice synthesis, backend processing, local storage, and hardware integration.
The goal was to develop a complete MVP of a cross-platform mobile app that allows children to listen to stories narrated in their parent's voice, even when the parent is away. The main challenge was to make AI-generated narration sound recognizably like the original speaker while keeping the voice recording process quick and simple.
The solution also had to ensure instant story playback without repeated generation delays, support offline listening, and enable Bluetooth connectivity with a physical mascot. These requirements called for an architecture that combined AI voice synthesis, backend processing, local storage, and hardware integration.
Solution
We developed Voicy, a mobile application for iOS and Android using Flutter, and integrated it with the ElevenLabs AI voice platform.
Parents can record a short voice sample directly in the app. Our backend handles the entire voice generation workflow, including sample uploads, individual voice provisioning, audiobook synthesis, and caching. Once a story is generated, it is stored locally on the device, allowing children to replay it instantly without additional API calls or an internet connection.
We also implemented QR code scanning to let parents add stories directly from their books, eliminating the need for a separate content management system. Additionally, we designed and developed the Bluetooth pairing experience and integrated the app with a physical mascot prototype, enabling playback of generated stories through the device.
We developed Voicy, a mobile application for iOS and Android using Flutter, and integrated it with the ElevenLabs AI voice platform.
Parents can record a short voice sample directly in the app. Our backend handles the entire voice generation workflow, including sample uploads, individual voice provisioning, audiobook synthesis, and caching. Once a story is generated, it is stored locally on the device, allowing children to replay it instantly without additional API calls or an internet connection.
We also implemented QR code scanning to let parents add stories directly from their books, eliminating the need for a separate content management system. Additionally, we designed and developed the Bluetooth pairing experience and integrated the app with a physical mascot prototype, enabling playback of generated stories through the device.
Results
We delivered a functional MVP of Voicy for both iOS and Android, combining AI-powered voice narration with mobile and hardware integration.
Key results include:
- Personalized AI narration: Stories are generated using a parent's voice through ElevenLabs.
- Instant playback: Each audiobook is synthesized once and cached locally for subsequent listening.
- Offline access: Downloaded stories remain available without an internet connection.
- Simplified content management: QR code scanning enables direct story access without a dedicated CMS.
- Hardware integration: Bluetooth connectivity allows finished audiobooks to be played through a physical mascot.
The result is an integrated digital and physical product that enables children to listen to familiar voices independently, while giving parents a simple way to make their presence felt even when they are away.
We delivered a functional MVP of Voicy for both iOS and Android, combining AI-powered voice narration with mobile and hardware integration.
Key results include:
- Personalized AI narration: Stories are generated using a parent's voice through ElevenLabs.
- Instant playback: Each audiobook is synthesized once and cached locally for subsequent listening.
- Offline access: Downloaded stories remain available without an internet connection.
- Simplified content management: QR code scanning enables direct story access without a dedicated CMS.
- Hardware integration: Bluetooth connectivity allows finished audiobooks to be played through a physical mascot.
The result is an integrated digital and physical product that enables children to listen to familiar voices independently, while giving parents a simple way to make their presence felt even when they are away.