Skip to main content

Voice Library Overview

The Voice Library is where you browse, preview, and select voices for your AI agents. Each voice has unique characteristics including gender, language support, and tonal qualities that affect how your agent sounds to callers.
The right voice significantly impacts caller perception and engagement. Take time to find one that matches your brand and use case.

Accessing the Voice Library

Navigate to Voices in the main navigation menu to access the Voice Library.

Browsing Voices

The Voice Library displays all available voices in a table format:
ColumnDescription
IDUnique voice identifier
NameVoice name
GenderMale, Female, or Neutral
LanguagesSupported languages
SamplePlay a sample
Custom AudioGenerate custom samples

Searching Voices

Use the search bar to filter voices by:
  • Name
  • Description
  • Language
  • Labels
Search for specific characteristics like “warm”, “professional”, or “friendly” to find voices that match your needs.

Previewing Voices

Playing Samples

Each voice has a pre-recorded sample:
1

Find the Voice

Locate the voice you want to preview.
2

Click Play

Click the “▶️ Play” button in the Sample column.
3

Listen

The sample plays through your speakers.
4

Stop

Click “⏹️ Stop” to end playback.

Generating Custom Audio

Test voices with your own text:
1

Enter Text

Type your custom text in the “Custom Text for Audio Generation” field.
2

Click Generate

Click “Generate” on the voice row you want to test.
3

Play

Once generated, click “▶️ Play” to hear the result.
4

Download (Optional)

Click “⬇️ Download” to save the audio file.
Use a sample greeting or common phrase from your use case to get an accurate preview of how the voice will sound.

Voice Settings

Fine-tune voice characteristics using the settings panel:

Speed

RangeDescription
0.70xSlower speech
1.00xNormal speed
1.20xFaster speech
Best practice: Start with 1.00x and adjust based on testing.

Naturalness (Stability)

ValueDescription
0.0More natural, slight variations
0.5Balanced
1.0More consistent, less natural
Best practice: Lower values (0.2-0.4) typically sound more human.

Consistency (Similarity Boost)

ValueDescription
0.0More variation
0.5Balanced
1.0Maximum consistency
High consistency values may cause audio artifacts. Test thoroughly before using values above 0.7.

Selecting a Voice for Your Agent

Once you’ve found the right voice:
1

Note the Voice ID or Name

Remember or copy the voice identifier.
2

Open Advanced Editor

Navigate to your agent in the Advanced Editor.
3

Go to Basic Settings

Open the Basic Settings section.
4

Select Voice

Choose the voice from the dropdown.
5

Save

Save your agent configuration.

Voice Characteristics

By Gender

  • Generally perceived as friendly and approachable
  • Popular for customer service and support
  • Works well for healthcare and wellness

By Use Case

Use CaseRecommended Characteristics
Customer SupportWarm, patient, clear
SalesEnergetic, persuasive, confident
HealthcareCalm, reassuring, professional
FinanceTrustworthy, professional, clear
TechnologyModern, clear, knowledgeable

Language Support

Voices may support one or multiple languages. Check the “Languages” column to ensure compatibility with your agent’s language setting. Supported Languages include:
  • 🇺🇸 English (US)
  • 🇬🇧 English (UK)
  • 🇪🇸 Spanish
  • 🇫🇷 French
  • 🇩🇪 German
  • 🇮🇹 Italian
  • 🇵🇹 Portuguese
  • And more…
Using a voice with a language it doesn’t support will result in poor quality or incorrect pronunciation.

Best Practices

Choose a voice that aligns with your brand personality. A luxury brand might want a sophisticated voice, while a tech startup might prefer a modern, casual one.
Think about who will be receiving calls. Different demographics may respond better to different voice characteristics.
Generate custom audio using actual phrases from your scripts to hear how the voice handles your specific content.
If using non-English languages, test pronunciation of common terms and names.
Fine-tune speed and naturalness to match your use case. Support calls might benefit from slower, clearer speech.

Next Steps