AI Voice Adventure Assistant
A browser-based voice storytelling assistant that turns a spoken story idea into a written and spoken adventure. FastAPI coordinates transcription, contextual OpenAI generation, and speech synthesis, with a bundled demo recording so visitors can try the complete flow immediately.
The problem
A browser-based voice storytelling assistant that turns a spoken story idea into a written and spoken adventure. FastAPI coordinates transcription, contextual OpenAI generation, and speech synthesis, with a bundled demo recording so visitors can try the complete flow immediately.
My contribution
I integrated browser audio capture to an asynchronous transcription, generation, and speech playback flow with recoverable errors.
Product features
- Browser recording, audio upload, and a bundled demo recording provide multiple input paths.
- Transcription, contextual reply generation, and speech synthesis run as a staged async workflow.
- Bounded in-memory conversation history supports follow-up turns and session reset.
- Recording duration, file formats, and upload sizes are constrained.
- Manual playback remains available when the browser blocks audio autoplay.
Engineering work
- Async audio pipeline: Coordinate transcription, contextual story generation, and speech synthesis behind one FastAPI request.
- Recoverable interaction: Show processing and playback states, constrain recordings and uploads, and keep manual playback available.
- Conversation state: Bound process-local history and commit a turn after the complete provider workflow succeeds.
Outcome & scope
Completes audio input → transcript → contextual story → playable MP3 in one interface. The deployed demo completed all three provider stages and played the generated reply; physical microphone recording was not tested in this review.
Public voice demo · Bundled recording available · AI-generated speech