temp commit, woring on playht

src/pipecat/services/playht.py

@@ -6,6 +6,7 @@
 
 import io
 import struct
+import time
 
 from typing import AsyncGenerator
 
@@ -25,7 +26,7 @@ except ModuleNotFoundError as e:
     raise Exception(f"Missing module: {e}")
 
 
-class PlayHTAIService(TTSService):
+class PlayHTTTSService(TTSService):
 
     def __init__(self, *, api_key: str, user_id: str, voice_url: str, **kwargs):
         super().__init__(**kwargs)
@@ -47,28 +48,40 @@ class PlayHTAIService(TTSService):
         self._client.close()
 
     async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
-        b = bytearray()
-        in_header = True
-        for chunk in self._client.tts(text, self._options):
-            # skip the RIFF header.
-            if in_header:
-                b.extend(chunk)
-                if len(b) <= 36:
-                    continue
-                else:
-                    fh = io.BytesIO(b)
-                    fh.seek(36)
-                    (data, size) = struct.unpack('<4sI', fh.read(8))
-                    logger.debug(
-                        f"first attempt: data: {data}, size: {hex(size)}, position: {fh.tell()}")
-                    while data != b'data':
-                        fh.read(size)
+        start_time = time.time()
+        ttfb = None
+        logger.debug(f"Generating TTS: [{text}]")
+
+        try:
+            b = bytearray()
+            in_header = True
+            sync_gen = self._client.tts(
+                text,
+                voice_engine="PlayHT2.0-turbo",
+                options=self._options)
+
+            # need to ask Aleix about this. frames are getting pushed.
+            # but playback is blocked
+            for chunk in sync_gen:
+                # skip the RIFF header.
+                if in_header:
+                    b.extend(chunk)
+                    if len(b) <= 36:
+                        continue
+                    else:
+                        fh = io.BytesIO(b)
+                        fh.seek(36)
                         (data, size) = struct.unpack('<4sI', fh.read(8))
-                        logger.debug(
-                            f"subsequent data: {data}, size: {hex(size)}, position: {fh.tell()}, data != data: {data != b'data'}")
-                    logger.debug("position: ", fh.tell())
-                    in_header = False
-            else:
-                if len(chunk):
-                    frame = AudioRawFrame(chunk, 16000, 1)
-                    yield frame
+                        while data != b'data':
+                            fh.read(size)
+                            (data, size) = struct.unpack('<4sI', fh.read(8))
+                        in_header = False
+                else:
+                    if len(chunk):
+                        if ttfb is None:
+                            ttfb = time.time() - start_time
+                            logger.debug(f"TTS ttfb: {ttfb}")
+                        frame = AudioRawFrame(chunk, 16000, 1)
+                        yield frame
+        except Exception as e:
+            logger.error(f"Error generating TTS: {e}")