Added new env variable and speech function for alternative TTS voice

.env.template

@@ -13,3 +13,4 @@ OPENAI_AZURE_DEPLOYMENT_ID=deployment-id-for-azure
 IMAGE_PROVIDER=dalle
 HUGGINGFACE_API_TOKEN=
 USE_MAC_OS_TTS=False
+USE_BRIAN_TTS=False

scripts/config.py

@@ -57,7 +57,10 @@ class Config(metaclass=Singleton):
 
         self.use_mac_os_tts = False
         self.use_mac_os_tts = os.getenv("USE_MAC_OS_TTS")
-        
+
+        self.use_brian_tts = False
+        self.use_brian_tts = os.getenv("USE_BRIAN_TTS")
+
         self.google_api_key = os.getenv("GOOGLE_API_KEY")
         self.custom_search_engine_id = os.getenv("CUSTOM_SEARCH_ENGINE_ID")
 
@@ -69,11 +72,13 @@ class Config(metaclass=Singleton):
 
         # User agent headers to use when browsing web
         # Some websites might just completely deny request with an error code if no user agent was found.
-        self.user_agent_header = {"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"}
+        self.user_agent_header = {
+            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"}
         self.redis_host = os.getenv("REDIS_HOST", "localhost")
         self.redis_port = os.getenv("REDIS_PORT", "6379")
         self.redis_password = os.getenv("REDIS_PASSWORD", "")
-        self.wipe_redis_on_start = os.getenv("WIPE_REDIS_ON_START", "True") == 'True'
+        self.wipe_redis_on_start = os.getenv(
+            "WIPE_REDIS_ON_START", "True") == 'True'
         self.memory_index = os.getenv("MEMORY_INDEX", 'auto-gpt')
         # Note that indexes must be created on db 0 in redis, this is not configureable.
 

scripts/speak.py

@@ -1,9 +1,9 @@
+import gtts
 import os
 from playsound import playsound
 import requests
 from config import Config
 cfg = Config()
-import gtts
 
 
 # TODO: Nicer names for these ids
@@ -14,6 +14,7 @@ tts_headers = {
     "xi-api-key": cfg.elevenlabs_api_key
 }
 
+
 def eleven_labs_speech(text, voice_index=0):
     """Speak text using elevenlabs.io's API"""
     tts_url = "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}".format(
@@ -33,23 +34,46 @@ def eleven_labs_speech(text, voice_index=0):
         print("Response content:", response.content)
         return False
 
+
+def brian_speech(text):
+    """Speak text using Brian with the streamelements API"""
+    tts_url = f"https://api.streamelements.com/kappa/v2/speech?voice=Brian&text={text}"
+    response = requests.get(tts_url)
+
+    if response.status_code == 200:
+        with open("speech.mp3", "wb") as f:
+            f.write(response.content)
+        playsound("speech.mp3")
+        os.remove("speech.mp3")
+        return True
+    else:
+        print("Request failed with status code:", response.status_code)
+        print("Response content:", response.content)
+        return False
+
+
 def gtts_speech(text):
     tts = gtts.gTTS(text)
     tts.save("speech.mp3")
     playsound("speech.mp3")
     os.remove("speech.mp3")
 
+
 def macos_tts_speech(text):
     os.system(f'say "{text}"')
 
+
 def say_text(text, voice_index=0):
     if not cfg.elevenlabs_api_key:
         if cfg.use_mac_os_tts == 'True':
             macos_tts_speech(text)
+        elif cfg.use_brian_tts == 'True':
+            success = brian_speech(text)
+            if not success:
+                gtts_speech(text)
         else:
             gtts_speech(text)
     else:
         success = eleven_labs_speech(text, voice_index)
         if not success:
             gtts_speech(text)
-