First Impressions: Initial Greeting in Larsa AI

The first few seconds of a call are crucial – they determine whether the customer stays on the line.
In Larsa AI, you have two options for your assistant’s first greeting:

1. Text-Based Initial Message

2. Custom Initial Audio

1. Initial Message

This is the first thing your AI assistant says when starting a call. It’s read exactly as written.

Best Practices:

• Keep it short (5–10 seconds).

• Get to the point quickly.

• Avoid long company introductions.

• Write the message exactly as you want it spoken, including proper diacritics if needed.

• Use punctuation for natural pauses.

• Write numbers as they should be spoken.

Examples:

"Hi! This is Sarah from ABC Company. How can I help you today?"
"Hi! This is Sarah from ABC Company... How can I help you today?"
"¡Hola! Soy María de ABC Company. ¿Cómo puedo ayudarte?"

2. Initial Audio

For the best first impression, you can use a pre-recorded audio file instead of text-to-speech.

Benefits:

• Professional quality

• Perfect pronunciation

• Human warmth in the voice

• Consistent delivery

• Higher customer retention

Setup Steps:

1. Record your greeting with a professional voice actor.

2. Upload the audio file in the assistant settings.

3. Clone the same voice for the rest of the conversation.

4. Enable initial audio playback.

Best Practices for Recording:

Recording Quality:

• Use professional equipment.

• Record in a quiet environment.

• Keep volume consistent.

• Save in a high-quality format.

Voice Matching:

• Use the same voice actor for cloning.

• Maintain consistent tone and style.

• Match energy levels to the purpose of the call.

Content Guidelines:

• Keep under 10 seconds.

• Include the company name.

• Clearly state the purpose.

• Sound warm and welcoming.

Example Script Structure:
[Greeting] + [Company Name] + [Purpose/Question]

"Hello! This is ABC Company calling about your recent inquiry. How are you today?"

3. Combining Both Methods

You can use both for maximum reliability:

• Primary: Initial audio for a professional, human-like touch.

• Backup: Initial text message if the audio is unavailable.

The system will use audio when available.

4. Testing Before Launch

Before going live:

• Call your assistant and listen to the greeting.

• Check for clear pronunciation.

• Ensure natural pauses.

• Verify proper volume levels.

• Confirm a smooth transition to the AI conversation.

5. Language Considerations

• Create separate initial messages or audio for each language.

• Use native speakers for recordings.

• Consider regional accents.

• Test with your target audience.

💡 Pro Tip: Record several versions of your initial audio and test which one gets the highest engagement rate.