Telnyx vs Vapi — voice agent latency
Two platforms, one identical agent script, dialled over real phone calls: Telnyx currently leads on both readings — the typical pause and the bad one. Every millisecond read from the call's own audio, never from a platform's timestamp.
Telnyx or Vapi — measured, reading by reading
Four readings, four verdicts. The three latency rows come from the same recordings of the same calls; the cost row comes from each platform's own billing API after the run, and carries the qualifiers noted under the table.
| Reading | Telnyx | Vapi | Measured winner |
|---|---|---|---|
| The pause on a normal turn (median TTFAB) | 1,296 ms | 1,558 ms | Telnyx |
| The pause when it is bad (p95) | 1,856 ms | 2,008 ms | Telnyx |
| How far the bad turns sit from the normal ones (tail ratio, p95 / median) | 1.43× | 1.29× | Vapi |
| Cost per invoiced minute (billing API, pooled) | $0.0500 | $0.0836 | Telnyx |
Tail ratio is the two readings divided — p95 ÷ median — and it is the one number a vendor cannot usefully publish about itself, because it only means anything when a single instrument produced both figures on the same calls. At 1.2× a platform's bad turns feel close to its normal ones. At 3× a caller regularly waits three times what the median promised. On a phone call that is where the damage is: past roughly two seconds of silence a caller assumes the line dropped and starts talking over the agent, which collides with the reply and derails the turn. So a platform can win the median and still do that to callers twice a conversation — read the tail ratio before the median, not after it.
On the cost row. Both figures are what the platform actually charged for this run, pulled from its own billing API and pooled — total cost over total invoiced minutes — never a published rate card. One of them carries a qualifier. For Telnyx, it bills a 60-second minimum, so the invoiced rate sits below its true cost per minute of conversation ($0.0500 against $0.0722). Read the winner with that in mind: it is the cheaper invoice on this run, not a guarantee it is the cheaper platform on yours.
There is no single fastest voice agent platform — which one wins depends on which pause your callers actually notice. Pick the workflow that matches yours:
- Most of your calls are ordinary back-and-forthTelnyxmedian 1,296 ms
Every turn is a normal question with a normal answer, so what matters is the wait a caller gets most of the time rather than the worst case.
- A caller must never think the line droppedElevenLabsp95 1,768 ms
Long pauses make callers talk over the agent or hang up, and that is a property of the slow turns, not the typical ones. Judge on the tail.
Full ranking, both readings, and the discard counts: the voice agent latency benchmark →
Telnyx vs Vapi — common questions
Is Telnyx or Vapi faster for voice agents?
On the pause a caller gets most of the time — median TTFAB — Telnyx is ahead: Telnyx 1,296 ms vs Vapi 1,558 ms. On the slow turns — p95 — Telnyx is ahead (1,856 ms vs 2,008 ms). Both figures are read from the audio of real phone calls, pooled over usable turns.
What is held equal between Telnyx and Vapi?
The agent: one system prompt, one greeting, one fixed set of questions in one order, dialled by the same caller over the same carrier. What is deliberately not held equal is each platform's own stack — The stack is not pinned. Each agent runs the model, speech recognition and voice the platform gives a new signup, and we record what it chose. Endpointing is the single exception — it is a timer inside the number we report, so where a platform exposes it we set it to 0.1 s. That one override is stated in full below. Pinning a stack measures a platform you would have to configure to match, not the one you would buy — and it excludes the vertically integrated platforms outright, since you cannot drop a third-party speech recogniser into a platform that owns its own.
Is Telnyx or Vapi cheaper?
Telnyx is cheaper on this run: Telnyx $0.0500 against Vapi $0.0836 per invoiced minute, taken from each platform's own billing API rather than a rate card and pooled across the run. One qualifier travels with those numbers. For Telnyx, it bills a 60-second minimum, so the invoiced rate sits below its true cost per minute of conversation ($0.0500 against $0.0722). So treat it as the cheaper invoice on this workload, not a guarantee about yours — a different call-length profile can reorder platforms that bill a minimum.
Why not use the latency Telnyx and Vapi publish themselves?
A platform measures from where it stands, and the caller is not standing there. We checked that two ways on this bench. A platform's own recording of a call reads roughly 550 ms earlier than our recording of the same call. The latency a platform reports for itself runs roughly 490 ms below what we measure from that call's audio. The two figures agree, and that agreement is the finding: both describe the moment a reply was produced, not the moment a caller heard it. Neither is dishonest — they answer a different question than the one a caller is asking. This board answers the caller's.
What is TTFAB (Time To First Audio Byte)?
Time from the moment the caller stops speaking to the moment the agent's audio starts — the silence a real caller sits through on every turn. Measured from a saved recording of the actual phone call, not from any API timestamp. Lower is better. Also written time to first audio byte, and closely related to what other boards call time to first byte (TTFB) or time to first audio (TTFA).
Do any measured voice agent platforms achieve sub-second or under-500 ms latency?
No. None of the 5 measured platforms has a median caller-experienced TTFAB below one second or 500 ms in the current benchmark. The lowest measured median is Telnyx at 1,296 ms. TTFAB here covers the complete pause from the caller finishing speech to hearing the agent's first audio over a real phone call; a server-side vendor TTFB can exclude endpointing, telephony, and network delay.
What does this comparison NOT measure?
Not measured: answer quality, voice quality, platform features, and published pricing plans — this board measures response latency, with the cost each platform actually invoiced for the same run reported beside it. Nor is it every platform. LiveKit Agents and Pipecat are frameworks you host yourself, so what a benchmark would time there is somebody's deployment rather than a product. The raw speech-to-speech APIs — OpenAI's Realtime API, Gemini Live — answer a socket, not a phone, and would need a telephony layer built around them first, which would then be inside the measurement. Twilio's own agent product simply has not been dialled yet. Until any of them is measured on the same script over the same carrier, this board has no number for it, and neither does anyone quoting one. Treat those as vendor claims until measured.