IBM Watson Speech to Text

Overview

IBM Watson® Speech to Text technology enables fast and accurate speech transcription in multiple languages for a variety of use cases, including but not limited to customer self-service, agent assistance and speech analytics. Get started fast with our advanced machine learning models out-of-the-box or customize them for your use case.

Features

Transcribe with greater accuracy

Train Watson Speech to Text on your unique domain language and specific audio characteristics.

Enjoy the security of IBM’s world-class data governance practices.

Built to support global languages and deployable on any cloud — public, private, hybrid, multicloud, or on-premises.

Improve speech recognition accuracy for extracting phrases, words, letters, numbers or lists.

Activate your voice application with speech models tuned for the customer care domain.

Recognize who said what in a multi-participant voice exchange.

Improve application response times by using speech transcription as it is generated and throughout the finalization process.

Use cases

Get more from every interaction

Agent assist

Boost agent productivity and success with real time assistance during calls using AI-powered document and intranet search. As the agent is speaking with a customer, Watson listens in on the conversation, transcribes the audio, searches for relevant content within documentation and feeds the answer back to the agent within seconds.

Customer self-service

Answer common call center queries using a Watson-powered virtual assistant on the phone.

Call analytics

Improve call center performance by mining conversation logs to quickly and accurately identify emerging call patterns, customer complaints, sentiment, non-compliant behavior and more.

Case studies

Real customers. Real results.

Bradesco

Bradesco is one of Brazil’s largest banks, with over 5,200 branches. Previously, when branch employees at Bradesco had questions about products or services, they had to call a central office. Long wait times for answers often left both employees and customers waiting.

Bradesco’s virtual agent solution (BIA) helps employees and customers find answers to complex questions about banking products and services. Used by 60,000 employees, BIA has increased customer satisfaction by more than 85% by reducing the time required to answer customer inquiries.

283,000

questions answered per month

95%

accuracy rate

Read case study

Humana

Humana, a leading US health insurer, struggled with high volumes of provider calls and costly transfers to live agents. Humana's interactive voice response (IVR) system was transfering too many calls to human agents, resulting in significant costs and lower customer satisfaction.

Humana's Voice Agent with Watson handles 7,000 live calls per day from 120 providers, answering questions about pre-service, medical eligibility, verification, authorization, and referral information without requiring a live agent. The solution enables providers to complete inquiries in approximately 2 minutes without human assistance and at one-third the cost of Humana's previous system.

7,000

calls per day

95%

accuracy in understanding customer inquires

Read case study

CodeObjects

CodeObjects developed InsurBot.ai to help insurance companies manage surges in customer inquiries following natural disasters. Using IBM Watson Speech to Text, watsonx Assistant, and Text to Speech, the solution automates policyholder interactions and claims-related requests. After Hurricane Michael, callers using InsurBot.ai experienced zero wait times, a significant improvement over previous waits that averaged eight minutes and could reach 30 minutes.

75%

reduction in average call time

Read case study

Vicom Infinity

Vicom Infinity, an IBM Business Partner, wanted to bring voice assistant technology to enterprise clients but needed stronger security for sensitive voice conversations and data. Using IBM Watson Speech to Text, watsonx Assistant, Text to Speech, and Hyper Protect Virtual Servers, it developed VIVA, a secure enterprise voice assistant that helps organizations process voice interactions in a security-rich cloud environment.

Read case study

MandarinMaster

MandarinMaster, an online Chinese-learning platform, needed a way to validate learners’ pronunciation and provide feedback on Mandarin’s challenging tone system. By integrating IBM Watson Speech to Text, the platform can analyze spoken responses and deliver immediate feedback. The result is a learning experience that simulates a personal tutor, helping learners build confidence and improve pronunciation.

Read case study

The Wilson Center

The Wilson Center, working with UNEP, needed a way to measure, analyze, and predict marine litter worldwide using data from many sources. IBM helped unify global environmental data and build AI models to forecast pollution trends. The solution also used IBM Watson Speech to Text to power "Sam," a digital human that makes marine litter information more accessible and engaging for the public.

Read case study

Pricing

Explore pricing options

Lite

500 minutes of free speech recognition a month and 38 pre-trained speech models.

Start for free

Plus

Tune your speech models to improve accuracy in recognition as well as transcription. Plus version includes unlimited minutes per month and 100 concurrent transcriptions.

View details

Premium

Provides large and security-sensitive firms with more capacity and data protection. Premium includes unlimited minutes per month and unlimited concurrent transcriptions.

Partner with IBM

Accelerate your business growth as an Independent Software Vendor (ISV) by innovating with IBM. Partner with us to deliver enhanced commercial solutions embedded with AI to better address clients’ needs.

Build AI-based solutions faster

Accelerate your growth with IBM