Inspiration
We were inspired by the idea that text should not just be read but also heard. From helping students learn better, to supporting accessibility, to giving creators an easy way to add voice, we wanted to make a tool that brings words to life instantly.
What it does
Svara is a text to speech app that converts any text into natural sounding audio in multiple languages. Users can type or paste text, generate speech in a few seconds, and save or share the audio for learning, content creation, or accessibility. Svara supports generating speech in 54 distinct voices across 9 languages.
How we built it
We used a cloud text to speech API to generate lifelike voices. On top of that, we built a simple Android app with a clean and modern interface. Users can input text, play it back immediately, and organize their generated speeches inside the app.
Challenges we ran into
Working within API usage limits and quotas
Making the app feel responsive while fetching and playing audio
Designing a smooth user flow from text input to playback and saving
Accomplishments that we're proud of
Built a fully working text to speech app within the hackathon timeframe
Integrated support for multiple languages and natural voices
Designed a simple experience that anyone can use without tutorials
What we learned
We learned how powerful cloud APIs can be when combined with a well designed interface. We also realized that user experience design is often more challenging than the technical integration itself.
What's next for Svara
We plan to add more voices and languages, improve offline support, and allow easy export for creators to use in videos and podcasts. We also want to explore personalization features so users can choose voices that truly fit their style.
Log in or sign up for Devpost to join the conversation.