Skip to content
EN
Demo
Platform
CallsQueues and routingIVR (phone menu)Smart transferAuto dialerBrowser-based softphoneClick-to-call
Messaging and customer dataUnified inboxForm builderCustomer portalCustomer success platform
ManagementHistorical reportingReal-time monitoringShift scheduling
Deployment and securityIn our cloudOn your serversHybrid deploymentData security
Platform →
Solutions
IndustriesRetailReal estateBanking and insuranceTravelHealthcareEducation
Customer serviceFAQ self-serviceOrder status without an agentAfter-hours coveragePeak days without overloadConversation quality assurance
SalesLead qualificationAppointment bookingRepeat salesLoyalty program
Outbound communicationPayment and overdue remindersNotifications and confirmationsPost-interaction survey
Who it's forBy company sizeBy role
Solutions →
AI agents
For customersVoice AI consultantAI consultant in chat
For employeesAI assistant for calls and salesAssistant for work questionsNew hire onboarding
TechnologyKnowledge baseSpeech analyticsAI connectorModelsData security
ServicesAI agent trainingMachine learning
AI agents →
Integrations
CRM systemsSalesforceHubSpotDynamics CRMSAP CXZoho CRMPipedrive
ERP systemsSAPNetSuiteBusiness CentralSageOdoo
Help desk and team chatZendeskFreshdeskServiceNowSlackMattermost
Messaging and socialWhatsAppViberInstagramFacebookSMSLive chat
Telephony, API, and AIAsteriskAMI, AGI, and ARIKamailioFreeSWITCHAPI and protocolsMCP connectors
Integrations →
Pricing
Company
ResourcesBlogCalculatorsComparisonsLibraryGlossary
ServicesOpen SourceImplementationDevelopmentSupportTraining
ContactsContact usAboutFacts and figures
Company →
Language: English
Demo

Glossary

Speech-to-text

Speech-to-text (STT) is technology that turns spoken words into text. In a contact center it powers AI voice agents, real-time suggested replies for agents, call transcripts, and speech analytics.

Why it mattersIt powers call search, speech analytics, and AI voice agents.

Also called: STT, automatic speech recognition, ASR, speech recognition, transcription

How it works

How it works

A neural network takes the audio and picks the most likely words. Recognition comes in two kinds. Streaming returns text while the person is still talking – AI voice agents and the agent's AI assistant cannot work without it. Batch processes calls that are already recorded – for speech analytics and search.

  • Streaming: text a fraction of a second after the words
  • Batch: transcripts of call recordings
  • Speaker separation: agent and customer on separate recording channels
  • Punctuation and numbers as digits, not words

Details

What affects accuracy

  • Audio quality: 8 kHz phone audio is harder to recognize than wideband
  • Background noise and people talking over each other
  • Accents, industry terms, and names of products, streets, and cities
  • How well the system knows English and whether you can add your own vocabulary
How it is measuredBy the share of wrongly recognized words (word error rate, WER). Test it on your own call recordings, not on demo samples.

Use

Where it is used

  • AI voice agents that understand normal speech
  • Suggested replies for agents during a call
  • Text search across all recorded calls
  • Speech analytics: topics, scripts, and emotions

In CONTACT.WORK

How it works in CONTACT.WORK

AI voice agents, the AI assistant, and speech analytics all need speech recognition. It is available both in the cloud and on your servers. The platform itself is free. Speech recognition is a separate paid service, or the model runs on your own GPU or a Mac mini.

The server calculator helps you pick the right hardware for running speech recognition on your own servers.

More

Where to use it

Speech analytics Check every call by its transcript Learn more AI voice agent Hand frequent calls to an AI agent Learn more AI assistant Give agents suggested replies during the conversation Learn more

Backlinks

Where it appears on the site 28

Platform 3

Solutions 9

more 3

AI agents 7

more 1

Services 1

Pricing 1

Comparisons 1

Home 1

Blog 5

Glossary

Related terms

Text-to-speechSpeech analyticsAI voice agentCall recordingSentiment analysis

Blog

Fresh from the blog

All articles →
Services · 7 min read Custom development of your contact center platform for your processes When contact center settings are not enough: integrations, modules, AI workflows. How to tell development from configuration and estimate the payback. Read the article → Management · 9 min read How many agents does your contact center need? Erlang C in plain English Calculate contact center staffing with Erlang C: workload, service level, shrinkage, and headcount by shift – all in one worked example. Read the article → Integrations · 7 min read CRM and phone system integration: what it does and how it works How to connect your phone system to your CRM: calls and recordings in the record, screen pop, click-to-call. What to decide first and how to check it works. Read the article →