diff --git a/CHANGELOG.md b/CHANGELOG.md
index 68cee9b50..9593a73fc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,27 +16,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   services that subclass `TTSService` can indicate whether the text in the
   `TTSTextFrame`s they push already contain any necessary inter-frame spaces.
 
-- New bot-output RTVI message to represent what the bot actually "says".
-  - RTVIBotOutputMessage / RTVIBotOutputMessageData — includes:
-    - spoken: bool — whether the text was spoken by TTS
-    - aggregated_by: Optional[str|\"word\"|\"sentence\"] — how the text was aggregated
-  - RTVIObserver now emits bot-output messages (bot-tts-text and bot-llm-text are still
-    supported and generated. bot-transcript is now deprecated in lieu of this new, more
-    thorough, message).
-
-- Introduced new `AggregatedLLMTextFrame` type to support representing effective llm
+- Introduced new `AggregatedTextFrame` type to support representing effective llm
+types an enum)
   output whether or not it is processed by the TTS. This new frame type includes the
   field `aggregated_by` to represent the conceptual format by which the given text
-  is aggregated. `TTSTextFrame`s now inherit from `AggregatedLLMTextFrame`.
+  is aggregated. `TTSTextFrame`s now inherit from `AggregatedTextFrame`.
 
 - New `bot-output` RTVI message to represent what the bot actually "says".
-  - The `RTVIObserver` now emits `bot-output` messages based off the new `AggregatedLLMTextFrame`s
+  - The `RTVIObserver` now emits `bot-output` messages based off the new `AggregatedTextFrame`s
     (`bot-tts-text` and `bot-llm-text` are still supported and generated, but `bot-transcript` is
     now deprecated in lieu of this new, more thorough, message).
   - The new `RTVIBotOutputMessage` includes the fields:
     - `spoken`: A boolean indicating whether the text was spoken by TTS
     - `aggregated_by`: A string representing how the text was aggregated ("sentence", "word",
-      "custom")
+      "my custom aggregation")
 
 - Updated the base aggregator type:
   - Introduced a new `Aggregation` dataclass to represent both the aggregated `text` and
@@ -86,10 +79,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
     - `PatternMatch` now extends `Aggregation` and provides richer info to handlers.
 
 - Added support for aggregating `LLMTextFrame`s from within the assistant `LLMAssistantAggregator`
-  when `skip_tts` is set to `True`, generating `AggregatedLLMTextFrame`s, therefore supporting
-  `bot-output` even when TTS is turned off. You can customize the aggregator used using the new
-  `llm_text_aggregator` field in the `LLMAssistantAggregatorParams`. NOTE: This feature is only
-  supported when using the new universal context.
+  when `skip_tts` is set to `True`, generating `AggregatedTextFrame`s, therefore supporting
+  the new `bot-output` event when TTS is turned off. You can customize the aggregator used using
+  the new `llm_text_aggregator` field in the `LLMAssistantAggregatorParams`. NOTE: This feature is
+  only supported when using the new `LLMContext`.
 
 ### Changed
 
@@ -116,11 +109,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - TTS flow respects aggregation metadata
   - `TTSService` accepts a new `skip_aggregator_types` to avoid speaking certain aggregation types
-    (asnow determined/returned by the aggregator)
-  - TTS services push `AggregatedLLMTextFrame` in addition to `TTSTextFrame`s when either an
+    (now determined/returned by the aggregator)
+  - TTS services push `AggregatedTextFrame` in addition to `TTSTextFrame`s when either an
     aggregation occurs that should not be spoken or when the TTS service supports word-by-word
     timestamping. In the latter case, the `TTSService` preliminarily generates an
-    `AggregatedLLMTextFrame`, aggregated by sentence to generate the full sentence content as early
+    `AggregatedTextFrame`, aggregated by sentence to generate the full sentence content as early
     as possible.
 
 ### Deprecated
diff --git a/src/pipecat/frames/frames.py b/src/pipecat/frames/frames.py
index 0fe41240a..f54ee58c6 100644
--- a/src/pipecat/frames/frames.py
+++ b/src/pipecat/frames/frames.py
@@ -12,6 +12,7 @@ and LLM processing.
 """
 
 from dataclasses import dataclass, field
+from enum import Enum
 from typing import (
     TYPE_CHECKING,
     Any,
@@ -358,22 +359,29 @@ class LLMTextFrame(TextFrame):
     pass
 
 
-@dataclass
-class AggregatedLLMTextFrame(TextFrame):
-    """Text frame representing an aggregation of LLMTextFrames.
+class AggregationType(Enum):
+    """Built-in aggregation strings."""
 
-    This frame contains multiple LLMTextFrames aggregated together for
-    processing or output along with a field to indicate how they are aggregated.
+    SENTENCE = "sentence"
+    WORD = "word"
+
+
+@dataclass
+class AggregatedTextFrame(TextFrame):
+    """Text frame representing an aggregation of TextFrames.
+
+    This frame contains multiple TextFrames aggregated together for processing
+    or output along with a field to indicate how they are aggregated.
 
     Parameters:
         aggregated_by: Method used to aggregate the text frames.
     """
 
-    aggregated_by: Literal["sentence", "word"] | str
+    aggregated_by: AggregationType | str
 
 
 @dataclass
-class TTSTextFrame(AggregatedLLMTextFrame):
+class TTSTextFrame(AggregatedTextFrame):
     """Text frame generated by Text-to-Speech services."""
 
     pass
diff --git a/src/pipecat/processors/aggregators/llm_response_universal.py b/src/pipecat/processors/aggregators/llm_response_universal.py
index 309a13634..8b2370967 100644
--- a/src/pipecat/processors/aggregators/llm_response_universal.py
+++ b/src/pipecat/processors/aggregators/llm_response_universal.py
@@ -24,7 +24,7 @@ from pipecat.audio.interruptions.base_interruption_strategy import BaseInterrupt
 from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import (
-    AggregatedLLMTextFrame,
+    AggregatedTextFrame,
     BotStartedSpeakingFrame,
     BotStoppedSpeakingFrame,
     CancelFrame,
@@ -627,6 +627,7 @@ class LLMAssistantAggregator(LLMContextAggregator):
             await self.push_frame(frame, direction)
         elif isinstance(frame, LLMFullResponseStartFrame):
             await self._handle_llm_start(frame)
+        # as a subclass of TextFrame, LLMTextFrame must be checked first
         elif isinstance(frame, LLMTextFrame):
             await self._handle_llm_text(frame)
         elif isinstance(frame, LLMFullResponseEndFrame):
@@ -854,7 +855,7 @@ class LLMAssistantAggregator(LLMContextAggregator):
         if not aggregate:
             return
 
-        llm_frame = AggregatedLLMTextFrame(text=aggregate.text, aggregated_by=aggregate.type)
+        llm_frame = AggregatedTextFrame(text=aggregate.text, aggregated_by=aggregate.type)
         await self.push_frame(llm_frame)
         if should_reset_aggregator:
             await self._llm_text_aggregator.reset()
diff --git a/src/pipecat/processors/frameworks/rtvi.py b/src/pipecat/processors/frameworks/rtvi.py
index 4ee48ee7e..e66aeef1b 100644
--- a/src/pipecat/processors/frameworks/rtvi.py
+++ b/src/pipecat/processors/frameworks/rtvi.py
@@ -32,7 +32,8 @@ from pydantic import BaseModel, Field, PrivateAttr, ValidationError
 
 from pipecat.audio.utils import calculate_audio_volume
 from pipecat.frames.frames import (
-    AggregatedLLMTextFrame,
+    AggregatedTextFrame,
+    AggregationType,
     BotStartedSpeakingFrame,
     BotStoppedSpeakingFrame,
     CancelFrame,
@@ -712,7 +713,7 @@ class RTVIBotOutputMessageData(RTVITextMessageData):
     """
 
     spoken: bool = True  # Indicates if the text has been spoken by TTS
-    aggregated_by: Optional[Literal["word", "sentence"] | str] = None
+    aggregated_by: Optional[AggregationType | str] = None
     # Indicates what form the text is in (e.g., by word, sentence, etc.)
 
 
@@ -1074,7 +1075,7 @@ class RTVIObserver(BaseObserver):
             await self.send_rtvi_message(RTVIBotTTSStartedMessage())
         elif isinstance(frame, TTSStoppedFrame) and self._params.bot_tts_enabled:
             await self.send_rtvi_message(RTVIBotTTSStoppedMessage())
-        elif isinstance(frame, AggregatedLLMTextFrame) and (
+        elif isinstance(frame, AggregatedTextFrame) and (
             self._params.bot_output_enabled or self._params.bot_tts_enabled
         ):
             if isinstance(frame, TTSTextFrame) and not isinstance(src, BaseOutputTransport):
@@ -1135,7 +1136,7 @@ class RTVIObserver(BaseObserver):
         if message:
             await self.send_rtvi_message(message)
 
-    async def _handle_aggregated_llm_text(self, frame: AggregatedLLMTextFrame):
+    async def _handle_aggregated_llm_text(self, frame: AggregatedTextFrame):
         """Handle aggregated LLM text output frames."""
         isTTS = isinstance(frame, TTSTextFrame)
         if self._params.bot_output_enabled:
diff --git a/src/pipecat/services/aws/nova_sonic/llm.py b/src/pipecat/services/aws/nova_sonic/llm.py
index ba537e49b..95240f748 100644
--- a/src/pipecat/services/aws/nova_sonic/llm.py
+++ b/src/pipecat/services/aws/nova_sonic/llm.py
@@ -27,6 +27,7 @@ from pydantic import BaseModel, Field
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.adapters.services.aws_nova_sonic_adapter import AWSNovaSonicLLMAdapter, Role
 from pipecat.frames.frames import (
+    AggregationType,
     BotStoppedSpeakingFrame,
     CancelFrame,
     EndFrame,
@@ -1027,7 +1028,7 @@ class AWSNovaSonicLLMService(LLMService):
         logger.debug(f"Assistant response text added: {text}")
 
         # Report the text of the assistant response.
-        frame = TTSTextFrame(text, aggregated_by="sentence")
+        frame = TTSTextFrame(text, aggregated_by=AggregationType.SENTENCE)
         frame.includes_inter_frame_spaces = True
         await self.push_frame(frame)
 
@@ -1062,7 +1063,9 @@ class AWSNovaSonicLLMService(LLMService):
                 # TTSTextFrame would be ignored otherwise (the interruption frame
                 # would have cleared the assistant aggregator state).
                 await self.push_frame(LLMFullResponseStartFrame())
-                frame = TTSTextFrame(self._assistant_text_buffer, aggregated_by="sentence")
+                frame = TTSTextFrame(
+                    self._assistant_text_buffer, aggregated_by=AggregationType.SENTENCE
+                )
                 frame.includes_inter_frame_spaces = True
                 await self.push_frame(frame)
             self._may_need_repush_assistant_text = False
diff --git a/src/pipecat/services/google/gemini_live/llm.py b/src/pipecat/services/google/gemini_live/llm.py
index ed28298ea..cdeae3921 100644
--- a/src/pipecat/services/google/gemini_live/llm.py
+++ b/src/pipecat/services/google/gemini_live/llm.py
@@ -27,6 +27,7 @@ from pydantic import BaseModel, Field
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.adapters.services.gemini_adapter import GeminiLLMAdapter
 from pipecat.frames.frames import (
+    AggregationType,
     BotStartedSpeakingFrame,
     BotStoppedSpeakingFrame,
     CancelFrame,
@@ -1646,7 +1647,7 @@ class GeminiLiveLLMService(LLMService):
             await self.push_frame(TTSStartedFrame())
             await self.push_frame(LLMFullResponseStartFrame())
 
-        frame = TTSTextFrame(text=text, aggregated_by="sentence")
+        frame = TTSTextFrame(text=text, aggregated_by=AggregationType.SENTENCE)
         # Gemini Live text already includes any necessary inter-chunk spaces
         frame.includes_inter_frame_spaces = True
 
diff --git a/src/pipecat/services/openai/realtime/llm.py b/src/pipecat/services/openai/realtime/llm.py
index 1d29908ba..766a9e980 100644
--- a/src/pipecat/services/openai/realtime/llm.py
+++ b/src/pipecat/services/openai/realtime/llm.py
@@ -19,6 +19,7 @@ from pipecat.adapters.services.open_ai_realtime_adapter import (
     OpenAIRealtimeLLMAdapter,
 )
 from pipecat.frames.frames import (
+    AggregationType,
     BotStoppedSpeakingFrame,
     CancelFrame,
     EndFrame,
@@ -686,7 +687,7 @@ class OpenAIRealtimeLLMService(LLMService):
         # We receive audio transcript deltas (as opposed to text deltas) when
         # the output modality is "audio" (the default)
         if evt.delta:
-            frame = TTSTextFrame(evt.delta, aggregated_by="sentence")
+            frame = TTSTextFrame(evt.delta, aggregated_by=AggregationType.SENTENCE)
             # OpenAI Realtime text already includes any necessary inter-chunk spaces
             frame.includes_inter_frame_spaces = True
             await self.push_frame(frame)
diff --git a/src/pipecat/services/openai_realtime_beta/openai.py b/src/pipecat/services/openai_realtime_beta/openai.py
index 115019538..d0cb39bf6 100644
--- a/src/pipecat/services/openai_realtime_beta/openai.py
+++ b/src/pipecat/services/openai_realtime_beta/openai.py
@@ -17,6 +17,7 @@ from loguru import logger
 
 from pipecat.adapters.services.open_ai_realtime_adapter import OpenAIRealtimeLLMAdapter
 from pipecat.frames.frames import (
+    AggregationType,
     BotStoppedSpeakingFrame,
     CancelFrame,
     EndFrame,
@@ -652,7 +653,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
     async def _handle_evt_audio_transcript_delta(self, evt):
         if evt.delta:
             await self.push_frame(LLMTextFrame(evt.delta))
-            await self.push_frame(TTSTextFrame(evt.delta, aggregated_by="sentence"))
+            await self.push_frame(TTSTextFrame(evt.delta, aggregated_by=AggregationType.SENTENCE))
 
     async def _handle_evt_speech_started(self, evt):
         await self._truncate_current_audio_response()
diff --git a/src/pipecat/services/tts_service.py b/src/pipecat/services/tts_service.py
index 0079f7708..2e1d7d421 100644
--- a/src/pipecat/services/tts_service.py
+++ b/src/pipecat/services/tts_service.py
@@ -23,7 +23,8 @@ from typing import (
 from loguru import logger
 
 from pipecat.frames.frames import (
-    AggregatedLLMTextFrame,
+    AggregatedTextFrame,
+    AggregationType,
     BotStartedSpeakingFrame,
     BotStoppedSpeakingFrame,
     CancelFrame,
@@ -388,7 +389,7 @@ class TTSService(AIService):
         elif isinstance(frame, TTSSpeakFrame):
             # Store if we were processing text or not so we can set it back.
             processing_text = self._processing_text
-            await self._push_tts_frames(frame.text, aggregated_by="sentence")
+            await self._push_tts_frames(frame.text, aggregated_by=AggregationType.SENTENCE)
             # We pause processing incoming frames because we are sending data to
             # the TTS. We pause to avoid audio overlapping.
             await self._maybe_pause_frame_processing()
@@ -494,8 +495,8 @@ class TTSService(AIService):
     async def _push_tts_frames(self, text: str, aggregated_by: str):
         if aggregated_by in self._skip_aggregator_types:
             # If this type of aggregation should be skipped, we just push the text as
-            # a basic AggregatedLLMTextFrame without sending it to TTS to speak.
-            await self.push_frame(AggregatedLLMTextFrame(text, aggregated_by=aggregated_by))
+            # a basic AggregatedTextFrame without sending it to TTS to speak.
+            await self.push_frame(AggregatedTextFrame(text, aggregated_by=aggregated_by))
             return
 
         # Remove leading newlines only
@@ -526,11 +527,11 @@ class TTSService(AIService):
                 # is set to False and these are sent word by word as part of the
                 # _words_task_handler in the WordTTSService subclass. However, to
                 # support use cases where an observer may want the full text before
-                # the audio is generated, we send an AggregatedLLMTextFrame here, but
+                # the audio is generated, we send an AggregatedTextFrame here, but
                 # we set append_to_context to False so it does not cause duplication
                 # in the context. This is primarily used by the RTVIObserver to
                 # generate a complete bot-output.
-                frame = AggregatedLLMTextFrame(text, aggregated_by=aggregated_by)
+                frame = AggregatedTextFrame(text, aggregated_by=aggregated_by)
                 frame.append_to_context = False
                 await self.push_frame(frame)
             await self.process_generator(self.run_tts(text))
@@ -669,7 +670,7 @@ class WordTTSService(TTSService):
                 frame = TTSStoppedFrame()
                 frame.pts = last_pts
             else:
-                frame = TTSTextFrame(word, aggregated_by="word")
+                frame = TTSTextFrame(word, aggregated_by=AggregationType.WORD)
                 frame.pts = self._initial_word_timestamp + timestamp
             if frame:
                 last_pts = frame.pts
diff --git a/tests/test_piper_tts.py b/tests/test_piper_tts.py
index 97b550ed9..05f571c24 100644
--- a/tests/test_piper_tts.py
+++ b/tests/test_piper_tts.py
@@ -13,7 +13,7 @@ import pytest
 from aiohttp import web
 
 from pipecat.frames.frames import (
-    AggregatedLLMTextFrame,
+    AggregatedTextFrame,
     ErrorFrame,
     TTSAudioRawFrame,
     TTSSpeakFrame,
diff --git a/tests/test_transcript_processor.py b/tests/test_transcript_processor.py
index be58f061e..d86e42101 100644
--- a/tests/test_transcript_processor.py
+++ b/tests/test_transcript_processor.py
@@ -11,6 +11,7 @@ from datetime import datetime, timezone
 from typing import List, Tuple, cast
 
 from pipecat.frames.frames import (
+    AggregationType,
     BotStartedSpeakingFrame,
     BotStoppedSpeakingFrame,
     CancelFrame,
@@ -130,11 +131,11 @@ class TestUserTranscriptProcessor(unittest.IsolatedAsyncioTestCase):
         frames_to_send = [
             BotStartedSpeakingFrame(),
             SleepFrame(),  # Wait for StartedSpeaking to process
-            TTSTextFrame(text="Hello", aggregated_by="word"),
-            TTSTextFrame(text="world!", aggregated_by="word"),
-            TTSTextFrame(text="How", aggregated_by="word"),
-            TTSTextFrame(text="are", aggregated_by="word"),
-            TTSTextFrame(text="you?", aggregated_by="word"),
+            TTSTextFrame(text="Hello", aggregated_by=AggregationType.WORD),
+            TTSTextFrame(text="world!", aggregated_by=AggregationType.WORD),
+            TTSTextFrame(text="How", aggregated_by=AggregationType.WORD),
+            TTSTextFrame(text="are", aggregated_by=AggregationType.WORD),
+            TTSTextFrame(text="you?", aggregated_by=AggregationType.WORD),
             SleepFrame(),  # Wait for text frames to queue
             BotStoppedSpeakingFrame(),
         ]
@@ -195,9 +196,9 @@ class TestUserTranscriptProcessor(unittest.IsolatedAsyncioTestCase):
         frames_to_send = [
             BotStartedSpeakingFrame(),
             SleepFrame(),
-            TTSTextFrame(text="", aggregated_by="word"),  # Empty text
-            TTSTextFrame(text="   ", aggregated_by="word"),  # Just whitespace
-            TTSTextFrame(text="\n", aggregated_by="word"),  # Just newline
+            TTSTextFrame(text="", aggregated_by=AggregationType.WORD),  # Empty text
+            TTSTextFrame(text="   ", aggregated_by=AggregationType.WORD),  # Just whitespace
+            TTSTextFrame(text="\n", aggregated_by=AggregationType.WORD),  # Just newline
             BotStoppedSpeakingFrame(),
             # Pipeline ends here; run_test will automatically send EndFrame
         ]
@@ -235,14 +236,14 @@ class TestUserTranscriptProcessor(unittest.IsolatedAsyncioTestCase):
         frames_to_send = [
             BotStartedSpeakingFrame(),
             SleepFrame(),
-            TTSTextFrame(text="Hello", aggregated_by="word"),
-            TTSTextFrame(text="world!", aggregated_by="word"),
+            TTSTextFrame(text="Hello", aggregated_by=AggregationType.WORD),
+            TTSTextFrame(text="world!", aggregated_by=AggregationType.WORD),
             SleepFrame(),
             InterruptionFrame(),  # User interrupts here
             SleepFrame(),
             BotStartedSpeakingFrame(),
-            TTSTextFrame(text="New", aggregated_by="word"),
-            TTSTextFrame(text="response", aggregated_by="word"),
+            TTSTextFrame(text="New", aggregated_by=AggregationType.WORD),
+            TTSTextFrame(text="response", aggregated_by=AggregationType.WORD),
             SleepFrame(),
             BotStoppedSpeakingFrame(),
         ]
@@ -299,8 +300,8 @@ class TestUserTranscriptProcessor(unittest.IsolatedAsyncioTestCase):
         frames_to_send = [
             BotStartedSpeakingFrame(),
             SleepFrame(),
-            TTSTextFrame(text="Hello", aggregated_by="word"),
-            TTSTextFrame(text="world", aggregated_by="word"),
+            TTSTextFrame(text="Hello", aggregated_by=AggregationType.WORD),
+            TTSTextFrame(text="world", aggregated_by=AggregationType.WORD),
             # Pipeline ends here; run_test will automatically send EndFrame
         ]
 
@@ -338,8 +339,8 @@ class TestUserTranscriptProcessor(unittest.IsolatedAsyncioTestCase):
         frames_to_send = [
             BotStartedSpeakingFrame(),
             SleepFrame(),
-            TTSTextFrame(text="Hello", aggregated_by="word"),
-            TTSTextFrame(text="world", aggregated_by="word"),
+            TTSTextFrame(text="Hello", aggregated_by=AggregationType.WORD),
+            TTSTextFrame(text="world", aggregated_by=AggregationType.WORD),
             SleepFrame(),  # Ensure messages are processed
             CancelFrame(),
         ]
@@ -401,8 +402,8 @@ class TestUserTranscriptProcessor(unittest.IsolatedAsyncioTestCase):
         frames_to_send = [
             BotStartedSpeakingFrame(),
             SleepFrame(),
-            TTSTextFrame(text="Assistant", aggregated_by="word"),
-            TTSTextFrame(text="message", aggregated_by="word"),
+            TTSTextFrame(text="Assistant", aggregated_by=AggregationType.WORD),
+            TTSTextFrame(text="message", aggregated_by=AggregationType.WORD),
             BotStoppedSpeakingFrame(),
         ]
 
@@ -439,7 +440,7 @@ class TestUserTranscriptProcessor(unittest.IsolatedAsyncioTestCase):
 
         # Test the specific pattern shared
         def make_tts_text_frame(text: str) -> TTSTextFrame:
-            frame = TTSTextFrame(text=text, aggregated_by="word")
+            frame = TTSTextFrame(text=text, aggregated_by=AggregationType.WORD)
             frame.includes_inter_frame_spaces = True
             return frame