Merge pull request #1251 from pipecat-ai/aleix/fish-tts-service-push-stop-frame

FishAudioTTSService should push TTSStoppedFrame

CHANGELOG.md

@@ -27,6 +27,9 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
 
 ### Fixed
 
+- Fixed a `FishAudioTTSService` issue where `TTSStoppedFrame` was not being
+  pushed.
+
 - Fixed an issue that `start_callback` was not invoked for some LLM services.
 
 - Fixed an issue that would cause `DeepgramSTTService` to stop working after an

src/pipecat/services/ai_services.py

@@ -209,7 +209,7 @@ class TTSService(AIService):
         # if True, TTSService will push TTSStoppedFrames, otherwise subclass must do it
         push_stop_frames: bool = False,
         # if push_stop_frames is True, wait for this idle period before pushing TTSStoppedFrame
-        stop_frame_timeout_s: float = 1.0,
+        stop_frame_timeout_s: float = 2.0,
         # if True, TTSService will push silence audio frames after TTSStoppedFrame
         push_silence_after_stop: bool = False,
         # if push_silence_after_stop is True, send this amount of audio silence

src/pipecat/services/elevenlabs.py

@@ -191,7 +191,6 @@ class ElevenLabsTTSService(WordTTSService, WebsocketService):
             aggregate_sentences=True,
             push_text_frames=False,
             push_stop_frames=True,
-            stop_frame_timeout_s=2.0,
             pause_frame_processing=True,
             sample_rate=sample_rate,
             **kwargs,

src/pipecat/services/fish.py

@@ -11,16 +11,13 @@ from loguru import logger
 from pydantic import BaseModel
 
 from pipecat.frames.frames import (
-    BotStoppedSpeakingFrame,
     CancelFrame,
     EndFrame,
     ErrorFrame,
     Frame,
-    LLMFullResponseEndFrame,
     StartFrame,
     StartInterruptionFrame,
     TTSAudioRawFrame,
-    TTSSpeakFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
 )
@@ -60,7 +57,12 @@ class FishAudioTTSService(TTSService, WebsocketService):
         params: InputParams = InputParams(),
         **kwargs,
     ):
-        super().__init__(pause_frame_processing=True, sample_rate=sample_rate, **kwargs)
+        super().__init__(
+            push_stop_frames=True,
+            pause_frame_processing=True,
+            sample_rate=sample_rate,
+            **kwargs,
+        )
 
         self._api_key = api_key
         self._base_url = "wss://api.fish.audio/v1/tts/live"

src/pipecat/services/rime.py

@@ -14,16 +14,13 @@ from loguru import logger
 from pydantic import BaseModel
 
 from pipecat.frames.frames import (
-    BotStoppedSpeakingFrame,
     CancelFrame,
     EndFrame,
     ErrorFrame,
     Frame,
-    LLMFullResponseEndFrame,
     StartFrame,
     StartInterruptionFrame,
     TTSAudioRawFrame,
-    TTSSpeakFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
 )
@@ -100,7 +97,6 @@ class RimeTTSService(AudioContextWordTTSService, WebsocketService):
             aggregate_sentences=True,
             push_text_frames=False,
             push_stop_frames=True,
-            stop_frame_timeout_s=2.0,
             pause_frame_processing=True,
             sample_rate=sample_rate,
             **kwargs,