Upload 6 files

app.py

@@ -1,6 +1,6 @@
 import os
 import gradio as gr
-from elevenlabs import set_api_key, voices, generate, Voice, VoiceSettings
+from elevenlabs import set_api_key, voices, generate, Voice, VoiceSettings, User
 import tempfile
 import speech_recognition as sr
 from pydub import AudioSegment
@@ -10,9 +10,25 @@ ELEVENLABS_API_KEY = os.getenv("ELEVENLABS_API_KEY")
 set_api_key(ELEVENLABS_API_KEY)
 
 def get_available_voices():
-    """Fetch all available voices from ElevenLabs account"""
-    available_voices = voices()
-    return {voice.name: voice.voice_id for voice in available_voices}
+    """Fetch only custom voices from ElevenLabs account"""
+    all_voices = voices()
+    custom_voices = {voice.name: voice.voice_id for voice in all_voices if not voice.category == "premade"}
+    return custom_voices
+
+def get_remaining_credits():
+    """Get remaining character credits from ElevenLabs"""
+    user = User.from_api()
+    subscription = user.subscription
+    return {
+        "character_count": subscription.character_count,
+        "character_limit": subscription.character_limit
+    }
+
+def format_credits_message(credits_info):
+    """Format credits information into a readable message"""
+    used = credits_info["character_limit"] - credits_info["character_count"]
+    total = credits_info["character_limit"]
+    return f"Credits: {credits_info['character_count']} / {total} characters remaining ({used} used)"
 
 def text_to_speech(text, voice_name, stability, clarity, style):
     """Convert text to speech using selected voice and parameters"""
@@ -32,10 +48,14 @@ def text_to_speech(text, voice_name, stability, clarity, style):
         )
     )
     
+    # Get updated credits
+    credits_info = get_remaining_credits()
+    credits_message = format_credits_message(credits_info)
+    
     # Save audio to temporary file
     with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_file:
         temp_file.write(audio)
-        return temp_file.name
+        return temp_file.name, credits_message
 
 def speech_to_text(audio_file):
     """Convert speech to text using speech recognition"""
@@ -61,11 +81,11 @@ def speech_to_speech(audio_file, voice_name, stability, clarity, style):
     # First convert speech to text
     text = speech_to_text(audio_file)
     if text.startswith("Error") or text.startswith("Could not"):
-        return None, text
+        return None, text, ""
     
     # Then convert text to speech
-    audio_output = text_to_speech(text, voice_name, stability, clarity, style)
-    return audio_output, text
+    audio_output, credits_message = text_to_speech(text, voice_name, stability, clarity, style)
+    return audio_output, text, credits_message
 
 # Get available voices
 VOICE_LIST = get_available_voices()
@@ -74,6 +94,10 @@ VOICE_LIST = get_available_voices()
 with gr.Blocks() as demo:
     gr.Markdown("# ElevenLabs Voice Generation")
     
+    # Display current credits
+    credits_info = get_remaining_credits()
+    credits_display = gr.Markdown(format_credits_message(credits_info))
+    
     with gr.Tab("Text to Speech"):
         with gr.Row():
             with gr.Column():
@@ -89,17 +113,17 @@ with gr.Blocks() as demo:
             
             with gr.Column():
                 audio_output = gr.Audio(label="Generated Audio")
+                credits_output = gr.Markdown()
         
         convert_btn.click(
             fn=text_to_speech,
             inputs=[text_input, voice_dropdown, stability, clarity, style],
-            outputs=audio_output
+            outputs=[audio_output, credits_output]
         )
     
     with gr.Tab("Speech to Speech"):
         with gr.Row():
             with gr.Column():
-                # Updated Audio component initialization
                 audio_input = gr.Audio(label="Input Audio", sources=["microphone", "upload"])
                 voice_dropdown_s2s = gr.Dropdown(choices=list(VOICE_LIST.keys()), label="Select Voice")
                 
@@ -113,11 +137,12 @@ with gr.Blocks() as demo:
             with gr.Column():
                 text_output = gr.Textbox(label="Recognized Text", lines=3)
                 audio_output_s2s = gr.Audio(label="Generated Audio")
+                credits_output_s2s = gr.Markdown()
         
         convert_btn_s2s.click(
             fn=speech_to_speech,
             inputs=[audio_input, voice_dropdown_s2s, stability_s2s, clarity_s2s, style_s2s],
-            outputs=[audio_output_s2s, text_output]
+            outputs=[audio_output_s2s, text_output, credits_output_s2s]
         )
 
 demo.launch()

discord-bot.py

@@ -0,0 +1,112 @@
+import os
+import discord
+from discord import app_commands
+from elevenlabs import set_api_key, voices, generate, Voice, VoiceSettings, User
+
+# Set up Discord intents
+intents = discord.Intents.default()
+client = discord.Client(intents=intents)
+tree = app_commands.CommandTree(client)
+
+# Set your ElevenLabs API key
+ELEVENLABS_API_KEY = os.getenv("ELEVENLABS_API_KEY")
+set_api_key(ELEVENLABS_API_KEY)
+
+def get_available_voices():
+    """Fetch only custom voices from ElevenLabs account"""
+    all_voices = voices()
+    return {voice.name: voice.voice_id for voice in all_voices if not voice.category == "premade"}
+
+def get_remaining_credits():
+    """Get remaining character credits from ElevenLabs"""
+    user = User.from_api()
+    subscription = user.subscription
+    return {
+        "character_count": subscription.character_count,
+        "character_limit": subscription.character_limit
+    }
+
+@tree.command(name="voice", description="Voice generation commands")
+@app_commands.describe(
+    action="Action to perform (list or create)",
+    text="Text to convert to speech",
+    voice_name="Name of the voice to use",
+    stability="Stability value (0-1)",
+    clarity="Clarity value (0-1)",
+    style="Style value (0-1)"
+)
+async def voice(
+    interaction: discord.Interaction,
+    action: str,
+    text: str = None,
+    voice_name: str = None,
+    stability: float = 0.5,
+    clarity: float = 0.75,
+    style: float = 0.5
+):
+    await interaction.response.defer()
+
+    if action.lower() == "list":
+        available_voices = get_available_voices()
+        voice_list = "\n".join([f"• {name}" for name in available_voices.keys()])
+        credits_info = get_remaining_credits()
+        credits_msg = f"\nCredits remaining: {credits_info['character_count']} / {credits_info['character_limit']}"
+        
+        await interaction.followup.send(f"Available voices:\n{voice_list}{credits_msg}")
+        
+    elif action.lower() == "create":
+        if not all([text, voice_name]):
+            await interaction.followup.send("Please provide both text and voice name.")
+            return
+            
+        available_voices = get_available_voices()
+        if voice_name not in available_voices:
+            await interaction.followup.send(f"Voice '{voice_name}' not found. Use /voice list to see available voices.")
+            return
+            
+        try:
+            voice_settings = VoiceSettings(
+                stability=stability,
+                similarity_boost=clarity,
+                style=style,
+                use_speaker_boost=True
+            )
+            
+            audio = generate(
+                text=text,
+                voice=Voice(
+                    voice_id=available_voices[voice_name],
+                    settings=voice_settings
+                )
+            )
+            
+            # Save audio to temporary file
+            with open("temp.mp3", "wb") as f:
+                f.write(audio)
+            
+            # Get updated credits
+            credits_info = get_remaining_credits()
+            credits_msg = f"Credits remaining: {credits_info['character_count']} / {credits_info['character_limit']}"
+            
+            await interaction.followup.send(
+                f"Generated audio with voice '{voice_name}'\n{credits_msg}",
+                file=discord.File("temp.mp3")
+            )
+            
+            # Clean up
+            os.remove("temp.mp3")
+            
+        except Exception as e:
+            await interaction.followup.send(f"Error generating audio: {str(e)}")
+    
+    else:
+        await interaction.followup.send("Invalid action. Use 'list' or 'create'.")
+
+@client.event
+async def on_ready():
+    await tree.sync()
+    print(f"Bot is ready and logged in as {client.user}")
+
+# Run the bot
+DISCORD_TOKEN = os.getenv("DISCORD_BOT_TOKEN")
+client.run(DISCORD_TOKEN)

docker-compose.yaml

@@ -0,0 +1,9 @@
+version: '3'
+services:
+  app:
+    build: .
+    ports:
+      - "7860:7860"
+    environment:
+      - GRADIO_SERVER_PORT=7860
+      - GRADIO_SERVER_NAME=0.0.0.0

dockerfile

@@ -0,0 +1,24 @@
+FROM python:3.10
+
+WORKDIR /code
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first to leverage Docker cache
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy your application
+COPY . .
+
+# Make start script executable
+RUN chmod +x start.sh
+
+# Expose the port Gradio will run on
+EXPOSE 7860
+
+# Run both applications
+CMD ["./start.sh"]

requirements.txt

@@ -3,4 +3,5 @@ elevenlabs==0.2.27
 SpeechRecognition==3.10.1
 pydub==0.25.1
 ffmpeg-python==0.2.0
-python-multipart==0.0.9
+python-multipart==0.0.9
+discord.py==2.3.2

start.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+# Start the Gradio app in the background
+python app.py &
+
+# Start the Discord bot
+python discord_bot.py