Speech to text: definition

Speech to text converts spoken audio into written text, which is what lets a voice agent understand a caller and what turns calls and meetings into searchable records.

It is the ear of any voice system: the step that turns what someone says into text a model can work with. Paired with text to speech (the voice) and a language model (the brain), it makes a voice agent possible.

Beyond voice agents, it unlocks call transcripts, meeting notes, and the content pipelines that turn a recording into articles and clips. Accuracy depends on audio quality and accent, so it is tuned to the real conditions.

Related terms

Voice agent: A voice agent is an AI system that answers or makes phone calls, understands speech, holds a natural conversation, and takes actions like booking or rescheduling, usually handing off to a human when needed.
Multimodal AI: Multimodal AI is a model that can take in or produce more than one kind of data, such as text plus images, audio, or video, rather than text alone.
Large language model (LLM): A large language model is a neural network trained on huge amounts of text to predict the next token, which lets it write, summarise, classify, and answer questions across almost any topic.