tcsenpai/agenticSeek
1
0
Fork 0
mirror of https://github.com/tcsenpai/agenticSeek.git synced 2025-06-06 19:15:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update text_to_speech.py

Browse Source 
updated the speak function , make it more sturctured , also added to play sound using afplay in macos and redirected linux or other to aplay , make sure the  display of audio  only work for jupyter notebooks not  in terminal. the name of audio file is directly used in code , standerized it.
This commit is contained in:
ganesh nikhil 2025-03-18 20:19:28 +05:30 committed by GitHub
parent d51f17fdad
commit 290b75de3f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
sources/text_to_speech.py
View File

@ -4,6 +4,7 @@ import soundfile as sf
import subprocess import subprocess
import re import re
import platform import platform
from sys import modules
class Speech(): class Speech():
""" """
@ -24,7 +25,7 @@ class Speech():
self.voice = self.voice_map[language][2] self.voice = self.voice_map[language][2]
self.speed = 1.2 self.speed = 1.2
def speak(self, sentence: str, voice_number: int = 1): def speak(self, sentence: str, voice_number: int = 1 , audio_file: str = 'sample.wav'):
""" """
Convert text to speech using an AI model and play the audio. Convert text to speech using an AI model and play the audio.
@ -38,17 +39,17 @@ class Speech():
sentence, voice=self.voice, sentence, voice=self.voice,
speed=self.speed, split_pattern=r'\n+' speed=self.speed, split_pattern=r'\n+'
) )
for i, (gs, ps, audio) in enumerate(generator): for i, (_, _, audio) in enumerate(generator):
audio_file = 'sample.wav' if 'ipykernel' in modules: #only display in jupyter notebook.
display(Audio(data=audio, rate=24000, autoplay=i==0), display_id=False) display(Audio(data=audio, rate=24000, autoplay=i==0), display_id=False)
sf.write(audio_file, audio, 24000) # save each audio file sf.write(audio_file, audio, 24000) # save each audio file
if platform.system().lower() == "windows": if platform.system().lower() == "windows":
import winsound import winsound
winsound.PlaySound(audio_file, winsound.SND_FILENAME) winsound.PlaySound(audio_file, winsound.SND_FILENAME)
elif platform.system().lower() == "linux": elif platform.system().lower() == "darwin": # macOS
subprocess.call(["aplay", audio_file])
else:
subprocess.call(["afplay", audio_file]) subprocess.call(["afplay", audio_file])
else: # linux or other.
subprocess.call(["aplay", audio_file])
def replace_url(self, url: re.Match) -> str: def replace_url(self, url: re.Match) -> str:
""" """