Deepgram Learn ·
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. Read 4 viewpoints with supporting evidence and source links.
Lines show the reading structure. Select an idea to read its explanation and evidence.
Synthesis
Function calling allows a voice agent to directly answer questions like 'Where’s my order?' rather than transferring the caller to a human agent.
Original excerpt
Function calling is how a voice agent answers "where's my order?" instead of transferring the caller to someone who can.
Jose Nicholas Francisco · Paragraph 1
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.
Continue exploring
voice agent function calling →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.
Original excerpt
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 · Paragraph 22
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.
Continue exploring
latency tolerance in voice interactions →The HumanMCP study measured a decline in function selection accuracy from 98% with 10 tools to 88% with 100 tools.
Original excerpt
The HumanMCP study measured a drop from 98% at 10 tools to 88% at 100.
Jose Nicholas Francisco · Paragraph 72
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.
Continue exploring
function selection accuracy →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.
Original excerpt
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 · Paragraph 83
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 .
Continue exploring
session limits in voice agents →Attributed passages with the context to verify them. Open the original text to check the source.
Original excerpt
The HumanMCP study measured a drop from 98% at 10 tools to 88% at 100.
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.
Original excerpt
Function calling is how a voice agent answers "where's my order?" instead of transferring the caller to someone who can.
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.
Original excerpt
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.
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.
Original excerpt
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 .
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 .
These viewpoints are linked to their original sources. Paraphrases are labeled and are not verbatim quotes.
Open transcript or source material (opens in a new tab)Report an issueJose Nicholas Francisco on function selection accuracy, latency tolerance in voice interactions, perceived latency thresholds. Explore 7 viewpoints by topic, with evidence from 2 sources.