dv-pipecat-ai 0.0.74.dev809__tar.gz → 0.0.74.dev810__tar.gz

{dv_pipecat_ai-0.0.74.dev809/src/dv_pipecat_ai.egg-info → dv_pipecat_ai-0.0.74.dev810}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-ai
-Version: 0.0.74.dev809
+Version: 0.0.74.dev810
 Summary: An open source framework for voice (and multimodal) assistants
 License-Expression: BSD-2-Clause
 Project-URL: Source, https://github.com/pipecat-ai/pipecat

{dv_pipecat_ai-0.0.74.dev809 → dv_pipecat_ai-0.0.74.dev810/src/dv_pipecat_ai.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-ai
-Version: 0.0.74.dev809
+Version: 0.0.74.dev810
 Summary: An open source framework for voice (and multimodal) assistants
 License-Expression: BSD-2-Clause
 Project-URL: Source, https://github.com/pipecat-ai/pipecat

{dv_pipecat_ai-0.0.74.dev809 → dv_pipecat_ai-0.0.74.dev810}/src/dv_pipecat_ai.egg-info/SOURCES.txt

@@ -200,6 +200,7 @@ src/pipecat/serializers/asterisk.py
 src/pipecat/serializers/base_serializer.py
 src/pipecat/serializers/convox.py
 src/pipecat/serializers/exotel.py
+src/pipecat/serializers/genesys.py
 src/pipecat/serializers/livekit.py
 src/pipecat/serializers/plivo.py
 src/pipecat/serializers/protobuf.py
@@ -272,6 +273,7 @@ src/pipecat/services/google/llm_openai.py
 src/pipecat/services/google/llm_vertex.py
 src/pipecat/services/google/rtvi.py
 src/pipecat/services/google/stt.py
+src/pipecat/services/google/test-google-chirp.py
 src/pipecat/services/google/tts.py
 src/pipecat/services/grok/__init__.py
 src/pipecat/services/grok/llm.py

dv_pipecat_ai-0.0.74.dev810/src/pipecat/serializers/genesys.py

@@ -0,0 +1,95 @@
+import base64
+import json
+from typing import Optional
+
+from pydantic import BaseModel
+
+from pipecat.audio.utils import create_default_resampler, pcm_to_ulaw, ulaw_to_pcm
+from pipecat.frames.frames import (
+    AudioRawFrame,
+    Frame,
+    InputAudioRawFrame,
+    InputDTMFFrame,
+    KeypadEntry,
+    StartFrame,
+    StartInterruptionFrame,
+    TransportMessageFrame,
+    TransportMessageUrgentFrame,
+)
+from pipecat.serializers.base_serializer import FrameSerializer, FrameSerializerType
+
+
+class GenesysFrameSerializer(FrameSerializer):
+    class InputParams(BaseModel):
+        genesys_sample_rate: int = 8000  # Default Genesys rate (8kHz)
+        sample_rate: Optional[int] = None  # Pipeline input rate
+
+    def __init__(self, session_id: str, params: InputParams = InputParams()):
+        self._session_id = session_id
+        self._params = params
+        self._genesys_sample_rate = self._params.genesys_sample_rate
+        self._sample_rate = 0  # Pipeline input rate
+        self._resampler = create_default_resampler()
+        self._seq = 1  # Sequence number for outgoing messages
+
+    @property
+    def type(self) -> FrameSerializerType:
+        return FrameSerializerType.TEXT
+
+    async def setup(self, frame: StartFrame):
+        self._sample_rate = self._params.sample_rate or frame.audio_in_sample_rate
+
+    async def serialize(self, frame: Frame) -> str | bytes | None:
+        if isinstance(frame, StartInterruptionFrame):
+            answer = {
+                "version": "2",
+                "type": "clearAudio",  # Or appropriate event for interruption
+                "seq": self._seq,
+                "id": self._session_id,
+            }
+            self._seq += 1
+            return json.dumps(answer)
+        elif isinstance(frame, AudioRawFrame):
+            data = frame.audio
+            # Convert PCM to 8kHz μ-law for Genesys
+            serialized_data = await pcm_to_ulaw(
+                data, frame.sample_rate, self._genesys_sample_rate, self._resampler
+            )
+            payload = base64.b64encode(serialized_data).decode("utf-8")
+            answer = {
+                "version": "2",
+                "type": "audio",
+                "seq": self._seq,
+                "id": self._session_id,
+                "media": {
+                    "payload": payload,
+                    "format": "PCMU",
+                    "rate": self._genesys_sample_rate,
+                },
+            }
+            self._seq += 1
+            return json.dumps(answer)
+        elif isinstance(frame, (TransportMessageFrame, TransportMessageUrgentFrame)):
+            return json.dumps(frame.message)
+
+    async def deserialize(self, data: str | bytes) -> Frame | None:
+        message = json.loads(data)
+        if message.get("type") == "audio":
+            payload_base64 = message["media"]["payload"]
+            payload = base64.b64decode(payload_base64)
+            # Convert Genesys 8kHz μ-law to PCM at pipeline input rate
+            deserialized_data = await ulaw_to_pcm(
+                payload, self._genesys_sample_rate, self._sample_rate, self._resampler
+            )
+            audio_frame = InputAudioRawFrame(
+                audio=deserialized_data, num_channels=1, sample_rate=self._sample_rate
+            )
+            return audio_frame
+        elif message.get("type") == "dtmf":
+            digit = message.get("dtmf", {}).get("digit")
+            try:
+                return InputDTMFFrame(KeypadEntry(digit))
+            except ValueError:
+                return None
+        else:
+            return None

{dv_pipecat_ai-0.0.74.dev809 → dv_pipecat_ai-0.0.74.dev810}/src/pipecat/services/elevenlabs/__init__.py

@@ -10,5 +10,6 @@ from pipecat.services import DeprecatedModuleProxy
 
 from .tts import *
 from .stt import *
+# Old
 
-sys.modules[__name__] = DeprecatedModuleProxy(globals(), "elevenlabs", "elevenlabs.[stt,tts]")
+sys.modules[__name__] = DeprecatedModuleProxy(globals(), "elevenlabs", "elevenlabs.tts")

dv_pipecat_ai-0.0.74.dev810/src/pipecat/services/google/test-google-chirp.py

@@ -0,0 +1,45 @@
+import asyncio
+import os
+
+from pipecat.frames.frames import TTSAudioRawFrame
+from pipecat.services.google.tts import GoogleTTSService
+
+
+async def test_chirp_tts():
+    # Get credentials from environment variable
+    credentials_path = (
+        "/Users/kalicharanvemuru/Documents/Code/pipecat/examples/ringg-chatbot/creds.json"
+    )
+
+    if not credentials_path or not os.path.exists(credentials_path):
+        raise ValueError(
+            "Please set GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account key file"
+        )
+
+    # Initialize the TTS service with Chirp voice
+    tts = GoogleTTSService(
+        credentials_path=credentials_path,
+        voice_id="en-US-Chirp3-HD-Charon",  # Using Chirp3 HD Charon voice
+        sample_rate=24000,
+    )
+
+    # Test text
+    test_text = "Hello, this is a test of the Google TTS service with Chirp voice."
+
+    print(f"Testing TTS with text: {test_text}")
+
+    # Generate speech
+    try:
+        async for frame in tts.run_tts(test_text):
+            if isinstance(frame, TTSAudioRawFrame):
+                print(f"Received audio chunk of size: {len(frame.audio)} bytes")
+            else:
+                print(f"Received frame: {frame.__class__.__name__}")
+
+        print("TTS generation completed successfully!")
+    except Exception as e:
+        print(f"Error during TTS generation: {str(e)}")
+
+
+if __name__ == "__main__":
+    asyncio.run(test_chirp_tts())