Koemei launches cloud-based speech recognition service

The Koemei Web Service platform enables transcription of video and audio content for captioning, indexing, search and discovery and SEO. At the core of Koemei Web Service is its speech decoding engine which converts the audio of every speaker into text.

Nearly $16 billion is spent annually on traditional transcription with approximately 120,000 transcriptionists in United States and is expected to grow 21 percent annually in the corporate and education markets. Koemei Web Services will be used in enterprises and by transcription service providers to increase accuracy and efficiency.

What separates Koemei from other services – and outdated manual transcription models – is Koemei’s unique cloud-based multi-speaker speech recognition platform and API for transcription of video and audio content at large scale.

“Koemei Web Services meets the need in business, media, governments, education and developers which produce an ever increasing amount of video but are limited to current manual, and costly, transcription methods,” said Mr. Temitope Ola, co-founder and CEO, Koemei. “We now offer a cloud-based, fully-automated machine transcription solution for enterprises to caption, index and monetize their content.”

“Current solutions are manual and costly ranging from $2.00 to $5.00 a minute and are not suitable or sustainable for large scale transcription needs of the media, government, or education. In the US alone, video and audio producers lose close to $5 billion annually through the inability of outdated manual methods to transcribe large amounts of content”, explained Mr. Ola.