Learn how to configure Speech Generation in the TIXAE Voice Suite. Use providers like ElevenLabs to generate human-like speech responses with customizable options for tone, background noise, and punctuation breaks.

​
🎤 Speech Generation Setup

​
1. Select a Speech Provider

  1. Navigate to the Voice Setup page in your TIXAE dashboard.
  2. Click on the Speech Gen tab.
  3. From the Speech Provider dropdown, select your preferred provider:
    • ElevenLabs is currently supported.
Speech Provider Dropdown

​
2. Choose a Voice

  1. Under the ElevenLabs Audio Library, available voices are listed.
  2. Browse through the options and preview each voice.
    • Use the play button to listen to a sample.
    • Adjust playback speed (e.g., 1x, 1.5x).
  3. Click “Use Voice” to select a voice for your setup.
Available Voices:
  • Marcus - Authoritative and deep
  • Sam - Chill, Southern California Male
  • Ali - Versatile and neutral
  • Lisa - Gentle, calm
  • Jessi - Neutral tone
  • Mimi - Soft and expressive

​
3. Advanced Options

Configure additional settings for speech generation:

​
🔊 Background Noise

Add environmental noise to simulate real-world settings.
  • Options include:
    • Restaurant
    • Office
    • Quiet Environment

​
✍️ Punctuation Breaks

  • Add pauses in the generated speech whenever punctuation (e.g., , or .) is detected.
  • Click ”+” to customize punctuation rules.
Reset to default settings if needed using the “Reset to default” button.

​
📝 Text-to-Speech Example

Here’s an example workflow for Speech Generation:
  1. Input Text: “Hello, how are you?”
  2. Selected Voice: Sam - Chill, Southern California Male
  3. Generated Speech: A natural-sounding voice plays the input text with optional background noise.

​
⚙️ Troubleshooting

​
Voice Not Showing?

  • Ensure your ElevenLabs API key is valid and configured correctly.

​
Speech Playback Delays?

  • Check your network connection.
  • Reduce background noise for faster processing.

​
🔗 Next Steps

Transcriber Configuration

Convert user speech into text.

Advanced Settings

Explore call recording, routing, and other configurations.
With Speech Generation set up, you can deliver human-like, customizable voice responses in your application. 🚀