What is latency (voice response time)?
The delay between the caller finishing speaking and hearing the agent's reply.
Latency (voice response time), explained
In voice AI, latency adds up across speech-to-text, the language model and text-to-speech, plus the phone network. Gaps of more than a second or two start to feel unnatural.
Voice agents reduce latency by streaming each step, starting speech before the full reply is written, and keeping servers close to callers.
See how these ideas come together in Chitti, Manolle's AI voice agent.
Related terms
- Turn detection (endpointing)Deciding when the caller has finished their turn so the agent can reply.
- Speech-to-text (STT)Technology that converts spoken audio into written text, also called automatic speech recognition (ASR).
- Text-to-speech (TTS)Technology that turns written text into spoken audio.
- Streaming (in voice AI)Processing audio and text in small pieces as they arrive, instead of waiting for the whole utterance.
See an AI voice agent at work on your calls.
See the complete system live: marketing, lead capture, AI voice calling, sales conversion, and analytics.