Merge pull request #28 from daily-co/update-playht-service

Update playht service

src/dailyai/services/playht_ai_service.py

@@ -1,36 +1,40 @@
 import io
-import os
 import struct
 from pyht import Client
-from dotenv import load_dotenv
 from pyht.client import TTSOptions
 from pyht.protos.api_pb2 import Format
 
-from services.ai_service import AIService
+from dailyai.services.ai_services import TTSService
 
 
-class PlayHTAIService(AIService):
-    def __init__(self, **kwargs):
-        super().__init__(**kwargs)
+class PlayHTAIService(TTSService):
 
-        self.speech_key = os.getenv("PLAY_HT_KEY") or ''
-        self.user_id = os.getenv("PLAY_HT_USER_ID") or ''
+    def __init__(
+        self,
+        *,
+        api_key,
+        user_id,
+        voice_url
+    ):
+        super().__init__()
+
+        self.speech_key = api_key
+        self.user_id = user_id
 
         self.client = Client(
             user_id=self.user_id,
             api_key=self.speech_key,
         )
         self.options = TTSOptions(
-            voice="s3://voice-cloning-zero-shot/820da3d2-3a3b-42e7-844d-e68db835a206/sarah/manifest.json",
+            voice=voice_url,
             sample_rate=16000,
             quality="higher",
             format=Format.FORMAT_WAV)
 
-    def close(self):
-        super().close()
+    def __del__(self):
         self.client.close()
 
-    def run_tts(self, sentence):
+    async def run_tts(self, sentence):
         b = bytearray()
         in_header = True
         for chunk in self.client.tts(sentence, self.options):

src/examples/foundational/01-say-one-thing.py

@@ -4,6 +4,7 @@
 
 from dailyai.services.daily_transport_service import DailyTransportService
 from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
+from dailyai.services.playht_ai_service import PlayHTAIService
 
 from examples.foundational.support.runner import configure
 
@@ -26,14 +27,23 @@ async def main(room_url):
             meeting_duration_minutes,
             mic_enabled=True
         )
+
+        """
         tts = ElevenLabsTTSService(
             aiohttp_session=session,
             api_key=os.getenv("ELEVENLABS_API_KEY"),
             voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
+        """
+        tts = PlayHTAIService(
+            api_key=os.getenv("PLAY_HT_API_KEY"),
+            user_id=os.getenv("PLAY_HT_USER_ID"),
+            voice_url=os.getenv("PLAY_HT_VOICE_URL"),
+        )
 
         # Register an event handler so we can play the audio when the participant joins.
         @transport.event_handler("on_participant_joined")
         async def on_participant_joined(transport, participant):
+            nonlocal tts
             if participant["info"]["isLocal"]:
                 return
 
@@ -46,6 +56,7 @@ async def on_participant_joined(transport, participant):
             await transport.stop_when_done()
 
         await transport.run()
+        del(tts)
 
 
 if __name__ == "__main__":