Skip to main content

Overview

Voice settings are crucial for creating natural, engaging conversations. Tabbly offers extensive voice customization options including voice library selection, custom voice cloning, and multi-language support.

Import Voices from Library

Voice Library

Tabbly’s voice library includes hundreds of high-quality voices across multiple languages, accents, and styles. Accessing the Library
  1. Navigate to Agent Settings > Voice
  2. Click Browse Voice Library
  3. Filter by language, gender, age, or style
  4. Preview voices by listening to samples
  5. Select your preferred voice

Voice Categories

Gender Options
  • Male voices
  • Female voices
  • Gender-neutral options
Age Ranges
  • Young adult (20-30)
  • Adult (30-50)
  • Mature (50+)
Styles
  • Professional
  • Friendly
  • Authoritative
  • Conversational
  • Energetic

Previewing Voices

  • Sample Phrases: Listen to standard phrases
  • Custom Text: Test with your own text
  • Conversation Samples: Hear full conversation examples
  • Side-by-Side Comparison: Compare multiple voices

Clone Voice (Custom Voice Cloning)

What is Voice Cloning?

Voice cloning allows you to create a custom voice that matches your brand, spokesperson, or specific requirements.

Requirements

Audio Requirements
  • Duration: Minimum 30 minutes of clean audio
  • Quality: High-quality recording (16kHz+ sample rate)
  • Format: WAV, MP3, or M4A
  • Content: Natural speech, varied sentences
Best Practices for Recording
  • Use a professional microphone
  • Record in a quiet environment
  • Speak naturally and clearly
  • Include varied sentence types
  • Maintain consistent tone and pace

Cloning Process

Step 1: Prepare Audio
  • Record or collect audio samples
  • Ensure high quality and clarity
  • Remove background noise
  • Normalize audio levels
Step 2: Upload Audio
  • Upload audio files to Tabbly
  • System validates quality and duration
  • Processing begins automatically
Step 3: Training
  • AI model trains on your audio
  • Process typically takes 24-48 hours
  • You’ll receive notification when complete
Step 4: Testing
  • Test cloned voice in Playground
  • Refine if needed
  • Deploy to agents

Use Cases

  • Brand Voice: Match your brand’s spokesperson
  • Multilingual: Clone voice in multiple languages
  • Consistency: Maintain consistent voice across all agents
  • Personalization: Use specific voices for different scenarios

Multi-Language Voice Selection

Supported Languages

Tabbly supports 30+ languages including:
  • English: US, UK, Australian, Indian variants
  • Spanish: Spain, Latin America variants
  • French: France, Canadian variants
  • German: Standard German
  • Hindi: Indian Hindi
  • Tamil, Telugu, Kannada: South Indian languages
  • Arabic: Modern Standard Arabic
  • Italian, Portuguese, Japanese, Korean: And many more

Language Selection

Primary Language
  • Set the main language for your agent
  • Most conversations will use this language
  • Default voice selected for primary language
Additional Languages
  • Add support for multiple languages
  • Automatic language detection
  • Seamless language switching during calls

Automatic Language Detection

  • Detects Caller Language: Identifies caller’s preferred language
  • Switches Automatically: Agent responds in detected language
  • Maintains Context: Conversation continues smoothly
  • Fallback Options: Defaults to primary language if detection fails

Testing Different Voices

Voice Testing Tools

Playground Testing
  • Test voices in realistic scenarios
  • Compare multiple voices side-by-side
  • Evaluate naturalness and clarity
  • Test with your actual conversation flows
A/B Testing
  • Test different voices with real callers
  • Compare performance metrics
  • Measure customer satisfaction
  • Choose best-performing voice

Evaluation Criteria

Naturalness
  • Does it sound human-like?
  • Are there any robotic artifacts?
  • Is the pacing natural?
Clarity
  • Is speech easy to understand?
  • Are words pronounced correctly?
  • Is there good articulation?
Appropriateness
  • Does it match your brand?
  • Is it suitable for your use case?
  • Does it resonate with your audience?
Performance
  • How do callers respond?
  • What’s the conversion rate?
  • What’s the customer satisfaction?

Voice Configuration Options

Speech Rate

Adjustable Speed
  • Slow: 0.8x normal speed
  • Normal: 1.0x normal speed
  • Fast: 1.2x normal speed
  • Custom: Set specific rate

Pitch and Tone

Pitch Adjustment
  • Higher pitch for energy
  • Lower pitch for authority
  • Natural pitch for balance
Tone Settings
  • Warm and friendly
  • Professional and formal
  • Energetic and enthusiastic
  • Calm and reassuring

Pauses and Emphasis

Natural Pauses
  • Configure pause duration
  • Add pauses for emphasis
  • Natural breathing patterns
Emphasis Points
  • Mark important words/phrases
  • Adjust emphasis intensity
  • Improve message clarity

Best Practices

Choose a voice that aligns with your brand personality and target audience.
Always test voices in realistic scenarios before deploying. What sounds good in isolation may not work in context.
Select voices that resonate with your target demographic. Age, gender, and accent preferences matter.
Use consistent voices across related agents to maintain brand consistency.
Prioritize clarity over style. A clear, understandable voice is more important than a unique one.

Troubleshooting

Voice Quality Issues
  • Check audio quality of source material
  • Ensure sufficient training data
  • Review voice settings and parameters
Language Detection Problems
  • Verify language settings
  • Check audio quality
  • Review detection sensitivity settings
Performance Issues
  • Test with different voices
  • Compare performance metrics
  • Gather caller feedback

Next Steps