Agents & tools
Voice Agent
A real-time conversational AI you talk to — over the phone, in an app, or through a wearable — that listens, reasons, and replies in voice.
01 ——
In plain English
A voice agent is an AI agent whose primary interface is spoken conversation. It listens to the user (speech-to-text), reasons about a response (LLM), and speaks back (text-to-speech), usually with low enough latency to feel like a real conversation.
What makes a good voice agent:
- Low latency — under 800ms turn-taking feels natural; over 1.5s feels broken
- Interruption handling — barge-in support, no awkward step-on-each-other
- Persona consistency — the voice, tone, and personality stay coherent
- Tool use — book appointments, look up orders, transfer to a human
- Memory — recognises returning callers and remembers context
Where they're deployed:
- Customer service — Sierra, Decagon, Parloa, Cresta
- Outbound sales — Air, Bland
- Healthcare — Hippocratic AI, Suki
- Real estate / scheduling — Lindy, Goodcall, Synthflow
- Developer infrastructure — Vapi, Retell, ElevenLabs Conversational AI
Voice agents are eating phone trees. The bar for what counts as "the human alternative" has risen dramatically since 2024.
02 ——
Related terms
Conversational AI
AI systems designed for natural back-and-forth dialogue with users — covering chatbots, voice assistants, and AI agents.
Speech-to-Text
AI that converts spoken audio into written text — the technology behind voice assistants, transcription tools, and meeting recorders.
Text-to-Speech
AI that converts written text into natural-sounding spoken audio — used for narration, accessibility, voice assistants, and content creation.
AI Agent
Software that uses an LLM to plan and act — picking tools, taking actions, and adapting based on results to complete a user’s goal.
Voice Cloning
AI that learns to mimic a specific person's voice from a short sample, then generates new speech in that voice from any text.
Chatbot
A program that simulates conversation with users — increasingly powered by LLMs to handle natural-language questions and tasks.
Back to glossaryLast reviewed May 2026