dtmf_aggregator

DTMF aggregation processor for converting keypad input to transcription.

This module provides a frame processor that aggregates DTMF (Dual-Tone Multi-Frequency) keypad inputs into meaningful sequences and converts them to transcription frames for downstream processing by LLM context aggregators.

class pipecat.processors.aggregators.dtmf_aggregator.DTMFAggregator(timeout: float = 2.0, termination_digit: KeypadEntry = KeypadEntry.POUND, prefix: str = 'DTMF: ', **kwargs)[source]

Bases: FrameProcessor

Aggregates DTMF frames into meaningful sequences for LLM processing.

The aggregator accumulates digits from InputDTMFFrame instances and flushes when:

  • Timeout occurs (configurable idle period)

  • Termination digit is received (default: ‘#’)

  • EndFrame or CancelFrame is received

Emits TranscriptionFrame for compatibility with existing LLM context aggregators.

__init__(timeout: float = 2.0, termination_digit: KeypadEntry = KeypadEntry.POUND, prefix: str = 'DTMF: ', **kwargs)[source]

Initialize the DTMF aggregator.

Parameters:

  • timeout – Idle timeout in seconds before flushing

  • termination_digit – Digit that triggers immediate flush

  • prefix – Prefix added to DTMF sequence in transcription

  • **kwargs – Additional arguments passed to FrameProcessor

async cleanup() → None[source]

Clean up resources.

async process_frame(frame: Frame, direction: FrameDirection) → None[source]

Process incoming frames and handle DTMF aggregation.

Parameters:

  • frame – The frame to process.

  • direction – The direction of frame flow in the pipeline.