CallMiner has introduced the Open Voice Transcription Standard (OVTS), a standard programming framework that enables organizations to leverage their existing or preferred speech recognition vendor with CallMiner.
The open architecture makes it easier for organizations to analyse interactions, gain insights from customer conversations at scale and drive business improvement, as well as achieve enhanced ROI on existing speech to text (STT) solutions and resources.
OVTS establishes foundational interoperability between a wide range of speech recognition providers and the CallMiner Eureka platform.
By providing a clear pathway for integration with any speech recognition provider via CallMiner’s OVTS API, organizations gain the flexibility needed to expand across regions based on language expertise, change transcription providers based on evolving business requirements, meet industry-specific capabilities, and more.
“CallMiner’s flexible platform accepts customer interactions from all sources – telephony and audio platforms, text-based interactions, such as chats, emails, surveys and reviews – and now with OVTS, transcribed audio from any speech recognizer,” said Bruce McMahon, VP of Product, CallMiner.
“The OVTS innovation allows CallMiner to take advantage of new features that speech recognition vendors offer, as well as deliver best-of-breed solutions to our customers based on use case.”
Founding members of OVTS include Nuance, Deepgram, Allo-Media and AppTek, who helped define the standard to meet the needs of the industry.
Additionally, OVTS enables organizations to take advantage of the most comprehensive conversation analytics by allowing them to leverage existing investments with large cloud vendors, such as Google Cloud, Microsoft Azure and Amazon Transcribe.
OVTS also simplifies and accelerates the integration of regional and language-specific speech recognition providers into the CallMiner platform. NTT-TX, a leading technology solution provider in Japan, leverages the OVTS API to power conversation analytics with its own speech recognition engine for the Japanese market.
“Organizations are having more customer conversations than ever before across a range of channels – from voice to chat and text,” said Jeff Gallino, CTO and founder, CallMiner.
“By giving organizations the flexibility to use their preferred speech recognition solution within CallMiner, whether it’s because of language capabilities or existing investment and platform considerations, they can effectively identify trends in agent performance, gain insights into customer experience and other key indicators needed to make improvements in the contact center and across the enterprise.”
The OVTS ecosystem is open for speech recognition providers to join and establish interoperability on a proactive basis. Through OVTS, vendors are also allowed access to develop against the CallMiner Eureka platform.
This blog post has been re-published by kind permission of CallMiner – View the original post
To find out more about CallMiner, visit their website.