aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2025-12-18 22:44:21 +01:00
Code Issues Packages Projects Releases Wiki Activity

fixed speech blocking main thread

Browse Source
This commit is contained in:
Bituq
2023-04-05 15:50:28 +02:00
parent 62dfd84599
commit 73bf928c1d
2 changed files with 23 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
requirements.txt
View File

@@ -1,7 +1,7 @@
beautifulsoup4 beautifulsoup4
colorama==0.4.6 colorama==0.4.6
openai==0.27.2 openai==0.27.2
playsound==1.3.0 playsound==1.2.2
python-dotenv==1.0.0 python-dotenv==1.0.0
pyyaml==6.0 pyyaml==6.0
readability-lxml==0.8.1 readability-lxml==0.8.1

15
scripts/speak.py
View File

@@ -4,6 +4,8 @@ import requests
from config import Config from config import Config
cfg = Config() cfg = Config()
import gtts import gtts
import threading
from threading import Lock
# TODO: Nicer names for these ids # TODO: Nicer names for these ids
@@ -14,17 +16,20 @@ tts_headers = {
"xi-api-key": cfg.elevenlabs_api_key "xi-api-key": cfg.elevenlabs_api_key
} }
mutex_lock = Lock() # Ensure only one sound is played at a time
def eleven_labs_speech(text, voice_index=0): def eleven_labs_speech(text, voice_index=0):
tts_url = "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}".format( tts_url = "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}".format(
voice_id=voices[voice_index]) voice_id=voices[voice_index])
formatted_message = {"text": text} formatted_message = {"text": text, "voice_settings": {"stability": 0.05, "similarity_boost": 0.8}}
response = requests.post( response = requests.post(
tts_url, headers=tts_headers, json=formatted_message) tts_url, headers=tts_headers, json=formatted_message)
if response.status_code == 200: if response.status_code == 200:
with mutex_lock:
with open("speech.mpeg", "wb") as f: with open("speech.mpeg", "wb") as f:
f.write(response.content) f.write(response.content)
playsound("speech.mpeg") playsound("speech.mpeg", True)
os.remove("speech.mpeg") os.remove("speech.mpeg")
return True return True
else: else:
@@ -34,11 +39,13 @@ def eleven_labs_speech(text, voice_index=0):
def gtts_speech(text): def gtts_speech(text):
tts = gtts.gTTS(text) tts = gtts.gTTS(text)
with mutex_lock:
tts.save("speech.mp3") tts.save("speech.mp3")
playsound("speech.mp3") playsound("speech.mp3", True)
os.remove("speech.mp3") os.remove("speech.mp3")
def say_text(text, voice_index=0): def say_text(text, voice_index=0):
def speak():
if not cfg.elevenlabs_api_key: if not cfg.elevenlabs_api_key:
gtts_speech(text) gtts_speech(text)
else: else:
@@ -46,3 +53,5 @@ def say_text(text, voice_index=0):
if not success: if not success:
gtts_speech(text) gtts_speech(text)
thread = threading.Thread(target=speak)
thread.start()