TextFrame: add skip_tts field

This lets a text frame bypass TTS while still being included in the LLM
context. Useful for cases like structured text that isn’t meant to be spoken but
should still contribute to context.

CHANGELOG.md

@@ -9,6 +9,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added `skip_tts` field to `TextFrame`. This lets a text frame bypass TTS while
+  still being included in the LLM context. Useful for cases like structured text
+  that isn’t meant to be spoken but should still contribute to context.
+
 - Added a `cancel_timeout_secs` argument to `PipelineTask` which defines how
   long the pipeline has to complete cancellation. When `PipelineTask.cancel()`
   is called, a `CancelFrame` is pushed through the pipeline and must reach the

src/pipecat/frames/frames.py

@@ -305,6 +305,11 @@ class TextFrame(DataFrame):
     """
 
     text: str
+    skip_tts: bool = field(init=False)
+
+    def __post_init__(self):
+        super().__post_init__()
+        self.skip_tts = False
 
     def __str__(self):
         pts = format_pts(self.pts)

src/pipecat/services/tts_service.py

@@ -296,7 +296,9 @@ class TTSService(AIService):
         """
         await super().process_frame(frame, direction)
 
-        if (
+        if isinstance(frame, TextFrame) and frame.skip_tts:
+            await self.push_frame(frame, direction)
+        elif (
             isinstance(frame, TextFrame)
             and not isinstance(frame, InterimTranscriptionFrame)
             and not isinstance(frame, TranscriptionFrame)