Google Text-to-Speech Audio Generator

A Python tool to generate multilingual podcast-ready audio files from text using Google Cloud Text-to-Speech and Translation APIs. Supports batch audio generation, automatic translation, and natural-sounding speech via SSML.

---

Features

• Batch Audio Generation: Create multiple audio files at once from different text inputs.
• Automatic Translation: Instantly translate your text to multiple languages and generate corresponding audio files.
• SSML Support: Use SSML tags to control pronunciation, pauses, pitch, and more for natural-sounding speech.
• Easy Setup: Simple Python script with minimal configuration.

Requirements

• Python 3.7+
• Google Cloud account with enabled Text-to-Speech and Translation APIs
• Service account key JSON file
• See requirements.txt for Python dependencies

Setup

1. Install dependencies:

   pip install -r requirements.txt

2. Google Cloud credentials:

   • Create a Google Cloud project and enable the Text-to-Speech API and Translation API.

   • Download a service account key JSON file.

   • Set the environment variable:

     export GOOGLE_APPLICATION_CREDENTIALS="/path/to/your/service-account-key.json"

Usage

1. Edit your input text or SSML as needed. Make sure to wrap content for translation between <speak> and </speak> tags.

2. Run the script:

   python tts_google.py

3. The generated filename.mp3 (or multiple files) will appear in the current directory, containing the spoken version of your input.

Limitations

• SSML Size: Maximum SSML input size is 5000 bytes. Larger inputs will cause an error.
• Voice Availability: Available voices are subject to Google Cloud Text-to-Speech API limitations.
• Translation Scope: Only text within <speak> and </speak> tags will be translated.

Contributing

Contributions are welcome! Please open an issue or submit a pull request with suggestions, bug fixes, or new features.