TranscriptProcessor

class pipecat.processors.transcript_processor.BaseTranscriptProcessor(**kwargs)

Bases: FrameProcessor

Base class for processing conversation transcripts.

Provides common functionality for handling transcript messages and updates.

class pipecat.processors.transcript_processor.UserTranscriptProcessor(**kwargs)

Bases: BaseTranscriptProcessor

Processes user transcription frames into timestamped conversation messages.

async process_frame(frame, direction)

Process TranscriptionFrames into user conversation messages.

Parameters:

• frame (Frame) – Input frame to process

• direction (FrameDirection) – Frame processing direction

class pipecat.processors.transcript_processor.AssistantTranscriptProcessor(**kwargs)

Bases: BaseTranscriptProcessor

Processes assistant TTS text frames into timestamped conversation messages.

This processor aggregates TTS text frames into complete utterances and emits them as transcript messages. Utterances are completed when: - The bot stops speaking (BotStoppedSpeakingFrame) - The bot is interrupted (StartInterruptionFrame) - The pipeline ends (EndFrame)

_current_text_parts

List of text fragments being aggregated for current utterance

_aggregation_start_time

Timestamp when the current utterance began

async process_frame(frame, direction)

Process frames into assistant conversation messages.

Handles different frame types: - TTSTextFrame: Aggregates text for current utterance - BotStoppedSpeakingFrame: Completes current utterance - StartInterruptionFrame: Completes current utterance due to interruption - EndFrame: Completes current utterance at pipeline end - CancelFrame: Completes current utterance due to cancellation

Parameters:

• frame (Frame) – Input frame to process

• direction (FrameDirection) – Frame processing direction

class pipecat.processors.transcript_processor.TranscriptProcessor

Bases: object

Factory for creating and managing transcript processors.

Provides unified access to user and assistant transcript processors with shared event handling.

Example

```python transcript = TranscriptProcessor()

pipeline = Pipeline(

[

transport.input(), stt, transcript.user(), # User transcripts context_aggregator.user(), llm, tts, transport.output(), transcript.assistant_tts(), # Assistant transcripts context_aggregator.assistant(),

]

)

@transcript.event_handler(“on_transcript_update”) async def handle_update(processor, frame):

print(f”New messages: {frame.messages}”)

```

user(**kwargs)

Get the user transcript processor.

Parameters:

**kwargs – Arguments specific to UserTranscriptProcessor

Return type:

UserTranscriptProcessor

assistant(**kwargs)

Get the assistant transcript processor.

Parameters:

**kwargs – Arguments specific to AssistantTranscriptProcessor

Return type:

AssistantTranscriptProcessor

event_handler(event_name)

Register event handler for both processors.

Parameters:

event_name (str) – Name of event to handle

Returns:

Decorator function that registers handler with both processors