Launched this week
Modulate Velma Preview

Modulate Velma Preview

Velma: Beyond transcripts, into true understanding.

10 followers

Visit website
Introducing Velma — the only voice-native Ensemble Listening Model designed to understand human speech in all its depth and nuance. Velma’s ELM architecture coordinates specialized AI models to reveal deeper audio insights and the underlying signals behind them, making results easy to explain and verify. Our Velma Preview allows anyone to test out a limited version of Velma with their own audio!
Modulate Velma Preview gallery image
Modulate Velma Preview gallery image
Modulate Velma Preview gallery image
Modulate Velma Preview gallery image
Free
Launch tags:Analytics•Artificial Intelligence•Audio
Launch Team
AssemblyAI
AssemblyAI
Build voice AI apps with a single API
Promoted

What do you think? …

Ken Morino
Maker
📌
Hey Product Hunt! I'm Ken, director of product at Modulate. We're exited to be launching a preview of Velma to showcase our newest model architecture for everyone to try out. Velma allows you to upload your own audio and get back analysis of it's content, both high level discoveries as well as underlying signals that were used. Our goal is to help facilitate deeper understand of conversations in a way that is both easy to explain and verify. For this preview version we've: - Optimized for cost over speed - Focused on generalized insights rather than industry-specific ones - Limited some of the model outputs to keep the experience accessible Would love to hear what you all think about Velma and if there is thing else you would like to see!