v3.0

🗣️ TTS Application v3.0

A powerful, cross-platform text-to-speech app featuring Google Cloud TTS and ElevenLabs integration, real-time playback, advanced voice controls, and flexible audio output options.

✨ What’s New in v3.0

🧠 Dual TTS Provider Support

• 🔄 Switch seamlessly between:
  • Google Cloud TTS – Enterprise-grade performance with SSML and audio profiles
  • ElevenLabs – Realistic voices with emotional expression and custom sliders

🎛️ Enhanced Voice Customization

• Google Cloud
  • 🎚️ Control speed, pitch, and audio profiles
  • 📝 Full SSML support (<break>, <prosody>, etc.)
• ElevenLabs
  • 🔧 Adjust stability, similarity boost, style, speaker boost, and speed

🖥️ All-New Cross-Platform UI

• 🌐 Available on Windows, macOS, and Linux
• 🎨 Dynamic UI that updates based on the selected provider
• 📊 Real-time quota usage tracking (for both providers)
• 🎧 Integrated audio playback, pause/resume, and stop controls
• 🔽 One-click download in selected format (.mp3, .wav, .ogg, etc.)

---

📥 Quick Start

1. Download the latest release from the Releases page
2. Add credentials:
   • 🔐 Google: credentials/google.json
   • 🔐 ElevenLabs: credentials/elevenlabs.json
3. Run the app:
   • Windows:

     .\TTS_App_Windows.exe

   • macOS:

     chmod +x TTS_App_macOS
     ./TTS_App_macOS

   • Linux:

     chmod +x TTS_App_Linux
     ./TTS_App_Linux

---

🧩 System Requirements

• OS:
  • Windows 10/11 (64-bit)
  • macOS 11.0+ (Big Sur and above)
  • Ubuntu 20.04+ (glibc ≥ 2.31)
• Python: 3.10 or later

---

🔐 Credentials Setup (For detailed setup instructions, please refer to UserGuide.md.)

🔑 Google Cloud TTS

1. Enable APIs in the Google Cloud Console:

   • Text-to-Speech API
   • Vertex AI API (for advanced voices)
   • Cloud Storage API (optional for caching)

2. Create a Service Account with roles:

   • Cloud Text-to-Speech API User
   • Vertex AI Service Agent
   • Storage Object Admin (if needed)

3. Generate JSON Key and save as:
   credentials/google.json

🔑 ElevenLabs TTS

1. Create an account at https://www.elevenlabs.io

2. Generate API Key from Profile > API Keys

3. Save as: credentials/elevenlabs.json

   {
     "api_key": "YOUR_API_KEY"
   }
   

🎮 How to Use

1. Select TTS Provider

Use the dropdown to switch between Google Cloud and ElevenLabs.
UI updates dynamically based on provider.

---

2. Enter Text

Use plain text or SSML (for Google Cloud):

<speak>
  Hello <break time="0.5s"/> world!
</speak>

3. Select Language & Voice

🟦 Google Cloud

• Choose from:
  • Standard voices
  • Wavenet voices
  • Neural2 voices
• Controls available:
  • Speed
  • Pitch
  • Audio Profile
• ✅ Full SSML support

🟨 ElevenLabs

• Choose from:
  • Multilingual v2
  • Turbo v2 models
• Controls available:
  • Stability
  • Similarity Boost
  • Style
  • Speaker Boost
  • Speed

---

4. Playback and Download

Use the control buttons for audio interaction:

• ▶️ Play
• ⏯️ Pause / Resume
• ⏹️ Stop
• ⬇️ Download the generated audio in your selected format

---

📁 Supported Audio Formats

Provider	Formats Supported	Default
Google Cloud	MP3, LINEAR16 (WAV), OGG_OPUS	MP3
ElevenLabs	MP3, PCM, ULAW	MP3

---

⚠️ Known Limitations

Google Cloud

• ❌ Some voices (e.g., Chirp) do not support SSML or pitch control
• 📉 API usage statistics may be unavailable

ElevenLabs

• ⏳ Some models take longer to generate audio
• 🔁 Retry logic may be triggered if response is delayed
• 📊 Usage stats may lag slightly behind real-time

---

🛠️ Developer Setup

# Install Python dependencies
pip install -r requirements.txt

# Build standalone executable
pyinstaller --onefile --add-data "credentials;credentials" src/main.py