AI case study

NottaMeeting transcript search

Search slowed to 1000ms as transcripts hit 30M hours. Migrating the vector engine cut latency to 100ms—10x faster.

Published|11 months ago

Key results

Faster Search Results
10x

Result highlights

Unlock 1 result highlight

The story

Context

A meeting transcription platform serving 10 million global users and processing over 30 million hours of audio across 58 languages.

Challenge

As the platform scaled to 30 million hours of transcription, the legacy vector search index hosted on a public cloud provider hit severe performance...

Solution
Unlock full story

Quotes

The company

AI transcription and meeting productivity tool for audio and video content.

IndustrySoftware & Platforms
LocationTokyo, Japan
Employees51-250
Founded2021

The AI provider

Vector database platform for building and scaling AI applications.

IndustrySoftware & Platforms
LocationRedwood City, CA, USA
Employees51-250
Founded2017

Similar Case Studies

Related implementations across industries and use cases

602 AI case studies in Software & Platforms

1,352 AI case studies in Product Engineering