PALLABI DHAR@Pallabi

Entertainment teams record hours of audio every week: artist interviews, label press conferences, fan meetings, music podcasts and broadcast segments. Reviewing it manually is slow, and important moments get missed. MediaPulse is a voice intelligence agent built on AssemblyAI that turns any of this audio into structured, searchable intelligence in minutes. Upload a file or paste an audio URL, and MediaPulse returns: - A full transcript with speaker labels and timestamps - Auto chapters with headlines and summaries, so teams can jump straight to the section they need - Sentence-level sentiment analysis to track how an artist, interview or press event lands - Entity and topic detection that picks out names, brands, organisations and places - Ask MediaPulse: a natural-language Q&A agent with one-click quick questions, using AssemblyAI's LLM Gateway with a built-in fallback that answers directly from the analysis MediaPulse is designed for K-entertainment use cases: PR teams monitoring coverage, A&R and artist management reviewing interviews, and content teams repurposing long-form audio into clips and summaries. Built with Python, Streamlit and the AssemblyAI Python SDK.

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.