wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Checkpoint from VS Code for coding agent session

Browse Source
This commit is contained in:
James Hush
2025-09-17 14:30:53 +08:00
parent 1fe27eb0a2
commit 451e4a9050
1 changed files with 17 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
src/pipecat/services/asyncai/tts.py
View File

@@ -27,7 +27,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame, TTSStoppedFrame,
) )
from pipecat.processors.frame_processor import FrameDirection from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.tts_service import InterruptibleTTSService, TTSService from pipecat.services.tts_service import TTSService, WebsocketWordTTSService
from pipecat.transcriptions.language import Language from pipecat.transcriptions.language import Language
from pipecat.utils.tracing.service_decorators import traced_tts from pipecat.utils.tracing.service_decorators import traced_tts
@@ -71,7 +71,7 @@ def language_to_async_language(language: Language) -> Optional[str]:
return result return result
class AsyncAITTSService(InterruptibleTTSService): class AsyncAITTSService(WebsocketWordTTSService):
"""Async TTS service with WebSocket streaming. """Async TTS service with WebSocket streaming.
Provides text-to-speech using Async's streaming WebSocket API. Provides text-to-speech using Async's streaming WebSocket API.
@@ -148,6 +148,7 @@ class AsyncAITTSService(InterruptibleTTSService):
self._receive_task = None self._receive_task = None
self._keepalive_task = None self._keepalive_task = None
self._started = False self._started = False
self._current_text = "" # Track current text for generating timestamps
def can_generate_metrics(self) -> bool: def can_generate_metrics(self) -> bool:
"""Check if this service can generate processing metrics. """Check if this service can generate processing metrics.
@@ -286,12 +287,24 @@ class AsyncAITTSService(InterruptibleTTSService):
elif msg.get("audio"): elif msg.get("audio"):
await self.stop_ttfb_metrics() await self.stop_ttfb_metrics()
# Start word timestamps and add the entire text as one "word"
# This generates transcription frames for the bot
self.start_word_timestamps()
if self._current_text.strip():
# Add the entire text as a single timestamp at time 0
await self.add_word_timestamps([(self._current_text, 0.0)])
frame = TTSAudioRawFrame( frame = TTSAudioRawFrame(
audio=base64.b64decode(msg["audio"]), audio=base64.b64decode(msg["audio"]),
sample_rate=self.sample_rate, sample_rate=self.sample_rate,
num_channels=1, num_channels=1,
) )
await self.push_frame(frame) await self.push_frame(frame)
# Add stop markers to end the word timestamps
await self.add_word_timestamps([("TTSStoppedFrame", 0), ("Reset", 0)])
elif msg.get("error_code"): elif msg.get("error_code"):
logger.error(f"{self} error: {msg}") logger.error(f"{self} error: {msg}")
await self.push_frame(TTSStoppedFrame()) await self.push_frame(TTSStoppedFrame())
@@ -335,6 +348,8 @@ class AsyncAITTSService(InterruptibleTTSService):
yield TTSStartedFrame() yield TTSStartedFrame()
self._started = True self._started = True
# Store the current text for generating timestamps
self._current_text = text
msg = self._build_msg(text=text, force=True) msg = self._build_msg(text=text, force=True)
try: try:
@@ -346,7 +361,6 @@ class AsyncAITTSService(InterruptibleTTSService):
await self._disconnect() await self._disconnect()
await self._connect() await self._connect()
return return
yield None
except Exception as e: except Exception as e:
logger.error(f"{self} exception: {e}") logger.error(f"{self} exception: {e}")