Finally, we wired our FastAPI backend to a live web frontend: drop in a WAV call, get an instant verdict with a confidence score, no Postman required. We also surfaced the semantic layer as a toggle right in the UI — "Usar transcripción semántica (ElevenLabs)" — so anyone can flip between our fast acoustic-only model and the ElevenLabs-powered semantic path on the same call, live, and see the latency/confidence tradeoff for themselves instead of taking our word for it.
Log in or sign up for Devpost to join the conversation.