Merge pull request #834 from pipecat-ai/aleix/transcription-are-text

frames: transcriptions should be TextFrames as before

CHANGELOG.md

@@ -83,8 +83,8 @@ async def on_audio_data(processor, audio, sample_rate, num_channels):
   delays. The sample rate of the provided sound files now need to match the
   sample rate of the output transport.
 
-- All input frames (text, audio, image, etc.) are now system frames. This means
+- Input frames (audio, image and transport messages) are now system frames. This
-  they are processed immediately by all processors instead of being queued
+  means they are processed immediately by all processors instead of being queued
   internally.
 
 - Expanded the transcriptions.language module to support a superset of

src/pipecat/frames/frames.py

@@ -177,6 +177,35 @@ class TextFrame(DataFrame):
         return f"{self.name}(pts: {pts}, text: [{self.text}])"
 
 
+@dataclass
+class TranscriptionFrame(TextFrame):
+    """A text frame with transcription-specific data. Will be placed in the
+    transport's receive queue when a participant speaks.
+
+    """
+
+    user_id: str
+    timestamp: str
+    language: Language | None = None
+
+    def __str__(self):
+        return f"{self.name}(user: {self.user_id}, text: [{self.text}], language: {self.language}, timestamp: {self.timestamp})"
+
+
+@dataclass
+class InterimTranscriptionFrame(TextFrame):
+    """A text frame with interim transcription-specific data. Will be placed in
+    the transport's receive queue when a participant speaks."""
+
+    text: str
+    user_id: str
+    timestamp: str
+    language: Language | None = None
+
+    def __str__(self):
+        return f"{self.name}(user: {self.user_id}, text: [{self.text}], language: {self.language}, timestamp: {self.timestamp})"
+
+
 @dataclass
 class LLMMessagesFrame(DataFrame):
     """A frame containing a list of LLM messages. Used to signal that an LLM
@@ -441,36 +470,6 @@ class TransportMessageUrgentFrame(SystemFrame):
         return f"{self.name}(message: {self.message})"
 
 
-@dataclass
-class TranscriptionFrame(SystemFrame):
-    """A text frame with transcription-specific data. Will be placed in the
-    transport's receive queue when a participant speaks.
-
-    """
-
-    text: str
-    user_id: str
-    timestamp: str
-    language: Language | None = None
-
-    def __str__(self):
-        return f"{self.name}(user: {self.user_id}, text: [{self.text}], language: {self.language}, timestamp: {self.timestamp})"
-
-
-@dataclass
-class InterimTranscriptionFrame(SystemFrame):
-    """A text frame with interim transcription-specific data. Will be placed in
-    the transport's receive queue when a participant speaks."""
-
-    text: str
-    user_id: str
-    timestamp: str
-    language: Language | None = None
-
-    def __str__(self):
-        return f"{self.name}(user: {self.user_id}, text: [{self.text}], language: {self.language}, timestamp: {self.timestamp})"
-
-
 @dataclass
 class UserImageRequestFrame(SystemFrame):
     """A frame user to request an image from the given user."""