Skip to content
Definition

What is DTMF fallback?

By Lewis CrookPublished

DTMF (dual-tone multi-frequency) fallback is the design pattern of capturing sensitive input — card numbers, PINs, account numbers — through keypad tones rather than speech, so the voice AI, recording layer, and underlying model never hear the digits. It is the standard PCI-safe capture pattern for voice AI deployments.

DTMF fallback uses the keypad to capture digits the model is not allowed to hear.

Why it matters for enterprise CX leaders

  • PCI DSS scope expands the moment card data enters the audio stream; DTMF capture keeps it out.
  • Pause-and-resume recording plus DTMF is the standard pattern for taking payments in voice AI without exploding the compliance scope.
  • Some deployments use DTMF as a graceful fallback when speech recognition repeatedly fails on a high-value input — a UX safety net as well as a compliance control.

Frequently asked questions

Is DTMF fallback required for PCI compliance?
Not by name, but a pattern that keeps card data out of the recorded audio and out of the model is required. DTMF capture routed to a PCI-scoped service is the most common implementation.
When else is DTMF used in voice AI?
As a UX fallback when speech recognition fails repeatedly on the same digit-heavy input, and for any input where audible repetition would be unacceptable — such as in noisy environments.
Does DTMF capture work with modern voice AI platforms?
Yes, but support varies. Confirm during evaluation that the platform supports DTMF capture, pause-and-resume recording, and routing of the captured digits to a separately scoped service without the model seeing them.

Used in

Related terms

  • Voice AIVoice AI is software that answers the phone, understands what the caller wants, and takes action — not just a smarter IVR.
  • Voice biometricsVoice biometrics confirms who the caller is by how they speak.
  • IVR replacementIVR replacement swaps menus and keypad input for natural conversation and actual resolution.
Last reviewed: 2026-06-26. Flag anything that no longer matches production reality on the corrections page.
Newsletter
Liked this? Get the next edition.

Plus the Voice AI Readiness Diagnostic in the welcome email.

Welcome email includes the Voice AI Readiness Diagnostic. No second list, no extra form.