From 68e4af8685dac029fc86ab9c43dcd451c1d96758 Mon Sep 17 00:00:00 2001
From: Master Blood <kosmix1999@gmail.com>
Date: Mon, 3 Apr 2023 22:38:01 -0700
Subject: [PATCH] Added a default (free) library for text to speech

Adds the gTTS (Google Text-to-Speech) Python library as a fallback for text-to-speech conversion in the speak.py file. The changes were made to ensure that users can still convert text to speech even if the ElevenLabs API key is not set or if the API encounters an error. Additionally, the requirements.txt file has been updated to include the new gTTS dependency.
---
 requirements.txt |  1 +
 scripts/speak.py | 23 ++++++++++++++++++++---
 2 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/requirements.txt b/requirements.txt
index 063931a951..7961106b6c 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -7,6 +7,7 @@ pyyaml==6.0
 readability-lxml==0.8.1
 requests
 tiktoken==0.3.3
+gTTS==2.3.1
 docker
 googlesearch-python
 google-api-python-client #(https://developers.google.com/custom-search/v1/overview) 
diff --git a/scripts/speak.py b/scripts/speak.py
index 2fbcbed26f..6fef41f83e 100644
--- a/scripts/speak.py
+++ b/scripts/speak.py
@@ -3,6 +3,8 @@ from playsound import playsound
 import requests
 from config import Config
 cfg = Config()
+import gtts
+
 
 # TODO: Nicer names for these ids
 voices = ["ErXwobaYiN019PkySvjV", "EXAVITQu4vr4xnSDxMaL"]
@@ -12,10 +14,9 @@ tts_headers = {
     "xi-api-key": cfg.elevenlabs_api_key
 }
 
-def say_text(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(
         voice_id=voices[voice_index])
-
     formatted_message = {"text": text}
     response = requests.post(
         tts_url, headers=tts_headers, json=formatted_message)
@@ -24,8 +25,24 @@ def say_text(text, voice_index=0):
         with open("speech.mpeg", "wb") as f:
             f.write(response.content)
         playsound("speech.mpeg")
-        # Delete audio file
         os.remove("speech.mpeg")
+        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 say_text(text, voice_index=0):
+    if not cfg.elevenlabs_api_key:
+        gtts_speech(text)
+    else:
+        success = eleven_labs_speech()
+        if not success:
+            gtts_speech(text)
+