Voice Agent Function Calling: Real-Time Data Lookup Guide

Deepgram Learn · Publicado el 12 sept 2026

A guide on voice agent function calling that covers direct answering capability, latency tolerance thresholds from a 2013 study, function selection accuracy decline with increasing tool count, and fixed two-hour session limits including warning and error signals. Lee 4 puntos de vista con sus evidencias y enlaces a las fuentes.

Jose Nicholas Francisco

Leer los puntos clave Abrir Editor

De un vistazo

Function calling enables direct answers instead of call transfers
Function calling allows a voice agent to directly answer questions like 'Where’s my order?' rather than transferring the caller to a human agent.
Ver el momento de apoyo · Párrafo 1
Perceived willingness drops significantly after 600–800 ms of silence
Ratings of perceived willingness drop noticeably at 600 ms and become statistically significant between 700 and 800 ms, based on the 2013 gap-tolerance study by Roberts and Francis.
Ver el momento de apoyo · Párrafo 22
Tool count degrades selection accuracy: 98% at 10 tools → 88% at 100
The HumanMCP study measured a decline in function selection accuracy from 98% with 10 tools to 88% with 100 tools.
Ver el momento de apoyo · Párrafo 72
Two-hour session limit applies regardless of in-flight lookups
Voice agent sessions expire after two hours; an in-flight function call does not extend the session, and the system emits MAXIMUM_SESSION_LENGTH_APPROACHING at 1h 55m and MAXIMUM_SESSION_LENGTH_REACHED at 2h.
Ver el momento de apoyo · Párrafo 83

Pasajes clave4

Pasajes atribuidos con contexto para verificarlos. Abra el texto original para comprobar la fuente.

Párrafo 72

function selection accuracy

Tool count degrades selection accuracy: 98% at 10 tools → 88% at 100

Extracto original

The HumanMCP study measured a drop from 98% at 10 tools to 88% at 100.

Jose Nicholas Francisco·12 sept 2026

Contexto

When the toolset grows, selection accuracy falls. Add functions one at a time and re-check selection accuracy after each. One lookup, three failure lines, and a filler function make a complete first release.

Párrafo 1

voice agent function calling

Function calling enables direct answers instead of call transfers

Extracto original

Function calling is how a voice agent answers "where's my order?" instead of transferring the caller to someone who can.

Jose Nicholas Francisco·12 sept 2026

Contexto

One order-status lookup on the inbound telephony agent pattern takes two round trips, three function calls, and a spoken line for every way it can fail.

Párrafo 22

latency tolerance in voice interactions

Perceived willingness drops significantly after 600–800 ms of silence

Extracto original

Ratings of perceived willingness drop off noticeably at 600ms in the classic 2013 gap-tolerance study from Roberts and Francis, and the difference turns statistically significant between 700 and 800ms.

Jose Nicholas Francisco·12 sept 2026

Contexto

Dead air is what the caller hears while your handler works, and it costs you fast. InjectAgentMessage is what covers that silence in the reference pattern.

Párrafo 83

session limits in voice agents

Two-hour session limit applies regardless of in-flight lookups

Extracto original

Yes, at two hours, and an in-flight lookup won't hold the session open. You get a Warning with MAXIMUM_SESSION_LENGTH_APPROACHING at 1 hour 55 minutes, then an Error with MAXIMUM_SESSION_LENGTH_REACHED at the two-hour limit .

Jose Nicholas Francisco·12 sept 2026

Contexto

KeepAlive doesn't extend it, and the docs don't cover a pending FunctionCallRequest at close. Finish or abandon it, then reconnect with agent.context .

Fuente y metodología

Estas perspectivas enlazan a sus fuentes originales. Las paráfrasis están identificadas y no son citas textuales.

Abrir transcripción o material de origen Reportar un problema