From c317e1917563a43bb5faf177660b38d877dd0fea Mon Sep 17 00:00:00 2001 From: jstahlbaum-fibernetics <143650857+jstahlbaum-fibernetics@users.noreply.github.com> Date: Fri, 12 Jul 2024 17:20:53 -0400 Subject: [PATCH] [Bug #628] correct coding errors in the google synthesiser (#629) * [Bug-628] correct coding errors in the google synthesiser * create_speech --> create_speech_uncached --------- Co-authored-by: Ajay Raj --- vocode/streaming/synthesizer/google_synthesizer.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/vocode/streaming/synthesizer/google_synthesizer.py b/vocode/streaming/synthesizer/google_synthesizer.py index 225ab2d5d2..acf89d7cea 100644 --- a/vocode/streaming/synthesizer/google_synthesizer.py +++ b/vocode/streaming/synthesizer/google_synthesizer.py @@ -5,7 +5,7 @@ from typing import Any import google.auth -from google.cloud import texttospeech as tts # type: ignore +from google.cloud import texttospeech_v1beta1 as tts # type: ignore from vocode.streaming.models.message import BaseMessage from vocode.streaming.models.synthesizer import GoogleSynthesizerConfig @@ -34,7 +34,7 @@ def __init__( # Select the type of audio file you want returned self.audio_config = tts.AudioConfig( audio_encoding=tts.AudioEncoding.LINEAR16, - sample_rate_hertz=24000, + sample_rate_hertz=synthesizer_config.sampling_rate, speaking_rate=synthesizer_config.speaking_rate, pitch=synthesizer_config.pitch, effects_profile_id=["telephony-class-application"], @@ -56,7 +56,7 @@ def synthesize(self, message: str) -> Any: ) # TODO: make this nonblocking, see speech.TextToSpeechAsyncClient - async def create_speech( + async def create_speech_uncached( self, message: BaseMessage, chunk_size: int, @@ -75,7 +75,7 @@ async def create_speech( in_memory_wav.setnchannels(1) in_memory_wav.setsampwidth(2) in_memory_wav.setframerate(output_sample_rate) - in_memory_wav.writeframes(response.audio_content) + in_memory_wav.writeframes(response.audio_content[44:]) output_bytes_io.seek(0) result = self.create_synthesis_result_from_wav(