This is a submission for the Murf AI Coding Challenge 2
What I Built:
I created AudioComic, a streaming “comic-to-voice” web app that transforms any uploaded comic PDF into a fully narrated, multi-voice audio experience—page by page. AudioComic converts each page to an image, processes it through a vision-enabled LLM to extract dialogue, scene context, and per-character emotional voice instructions, and then synthesizes each character’s lines via Murf AI’s TTS and voice-changer in real time, keeping a running story summary to maintain narrative flow.
Demo Video:
Code Repository:
https://github.com/Kavish2040/AudioComic
How I Used Murf API:
1. Real-Time Audio Generation
Used Murf AI's TTS API to convert extracted comic panel text into high-quality MP3 audio files with professional voice synthesis for immersive storytelling experience.
2. Multi-Language Voice Support
Implemented Murf AI's language-specific voice library to provide native speaker narration in 10+ languages (English, Spanish, French, German, etc.) for global accessibility.
3. Dynamic Character Voice Assignment
Leveraged Murf AI's diverse voice portfolio to automatically assign different voices (male, female, narrator, child) based on comic character analysis and panel content.
4. Translation + Localization Pipeline
Integrated Murf AI's translation and TTS APIs to create a complete localization workflow that translates comic text and generates native-language audio narration.
Use Case & Impact
AudioComic makes comics accessible to:
• People who don't want to wait for Animation adaptation!
• Visually impaired readers, by converting visuals into rich, multi-voice audio.
• Multitaskers, who can listen while commuting or exercising.
• Educators & storytellers, who can add thematic voice effects for deeper immersion.
By automating dynamic voice configurations and delivering context-aware narration, AudioComic streamlines the audio adaptation of graphic stories and opens up a new inclusive medium.
Future Development
• Anime-Style Adaptation: Evolve from static panels to dynamic, panel-by-panel animations with character motion and camera pans.
• Immersive SFX & Music: Layer in sound effects (doors creaking, explosions) and background scores timed to panel transitions.
• Video Effects & Transitions: Add visual effects—motion lines, lighting shifts, scene fades—to mimic anime pacing.
• Precision Panel Timing: Leverage your existing panel detector to sync voice, SFX, and animations for a truly cinematic comic-to-anime experience.
My Partners in Dev:
Live Website
audiocomic
Top comments (0)