Speech-to-Text (STT)

The technology that converts spoken audio into written text in real time, enabling AI voice agents to understand what a caller is saying.

Technical definition

Modern STT systems use deep neural networks (typically transformer-based architectures) trained on thousands of hours of labeled speech data. They process audio in streaming mode — transcribing speech as it's spoken with sub-second latency. Smart formatting automatically applies capitalization, punctuation, numerals, and date formatting to the output text.

How Verabase uses Speech-to-Text

Verabase uses Deepgram Nova-3 for speech-to-text, connected via your own Deepgram API key (BYOK). Audio from the browser's WebRTC connection is streamed to Deepgram in real time. The transcribed text is then passed through your agent's RAG pipeline to generate a response. Supported languages include English, Spanish, French, German, Japanese, and more. Smart formatting is enabled by default, meaning numbers, times, and dates are structured automatically.

Why it matters for support teams

The quality of speech-to-text directly determines the quality of your voice AI. A misheard word can completely change the meaning of a question, leading to wrong answers. Modern STT models like Deepgram Nova-3 achieve word error rates under 8%, making AI voice agents practical for production use cases where accuracy matters.

Related terms

How Verabase Handles Self-Healing Knowledge

The standard industry approach relies on support agents manually flagging stale content and technical writers updating documentation weeks later. Verabase completely upends this model through an autonomous AI platform that identifies knowledge gaps the moment an AI agent encounters a question it cannot answer.

Rather than requiring manual intervention, our visual RAG engine drafts a proposed fix. It analyzes the context of the user's question, reviews your existing knowledge base for conflicts, and creates a clear, structured article or snippet. All you need to do is click 'Approve'. This ensures your AI agents continually get smarter over time without adding to your support team's workload.

Security First Architecture

Many legacy platforms bolt AI onto their existing infrastructure, creating potential data leaks between tenants or exposing sensitive internal documents to end-users. Verabase is built from the ground up with a Bring Your Own Key (BYOK) architecture, enterprise-grade access controls, and strict semantic boundaries. This means your private engineering documents never accidentally leak into customer-facing agent responses.