Tts

📸 Screenshots

Here are visual examples of this section:

Tts - Worker Configuration Interface

The TTS worker converts text input into audio speech using either Google Text-to-Speech or OpenAI's speech synthesis API. It automatically detects the language of the input text and selects appropriate voices, with support for multiple audio formats optimized for various platforms including Telerivet compatibility.

2. Configuration Parameters

The Worker accepts the following parameters:

engine: Specifies the text-to-speech engine to use. Can be either "google" or "openai". Defaults to "google" for backward compatibility.

3. Input/Output Handles

input: Input handle - accepts string text to be converted to speech
output: Output handle - returns audio object with base64-encoded audio data and file extension

4. Usage Examples with Code

// Configure TTS worker with OpenAI engine
const ttsWorker = {
  parameters: {
    engine: "openai"
  },
  fields: {
    input: { value: "Hello, this is a test message." },
    output: { value: null }
  }
}

// The output will contain:
// { audio: "base64EncodedAudioData", ext: "ogg" }

5. Integration Examples

This worker is commonly used in voice messaging workflows, automated phone systems, and accessibility applications where text content needs to be converted to audio format.

6. Best Practices

Use Google TTS for better language detection and voice selection capabilities
Use OpenAI TTS for consistent voice quality across different languages
Keep text input under reasonable length limits to avoid API timeouts
Ensure proper API keys are configured for your chosen engine

7. Troubleshooting Tips

Verify that the correct API keys (Google or OpenAI) are properly configured
Check that input text is not empty or null
For Google TTS, ensure both Google TTS and Google Translate API keys are available for language detection
If audio playback fails, verify the output format is compatible with your target platform

Tts