> ## Documentation Index
> Fetch the complete documentation index at: https://docs.movoice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Audio tab

# Audio Tab

The **Audio Tab** is where you select the "Voice" of your agent and fine-tune its acoustic properties.

## Voice Libraries

Movoice AI integrates with multiple providers to offer hundreds of realistic voices.

1. **ElevenLabs**: Known for human-like prosody and emotion.
2. **Sarvam AI**: The best choice for natural Indian regional languages (Hindi, Odia, etc.).
3. **Deepgram Aura**: Designed specifically for high-speed conversational AI.
4. **PlayHT**: Extensive library of cloned and synthetic voices.

## Tuning Your Agent's Voice

### 1. Stability

Controls how much the voice varies between sentences.

* **High**: Consistent, clear, and professional.
* **Low**: More expressive, varying pitch and tone (useful for friendly sales reps).

### 2. Similarity Boost

Determines how closely the generated audio matches the original voice sample used to train the model.

### 3. Speed Control

Adjust the delivery speed of your agent.

* **0.9x**: Slightly slower, helpful for older audiences or complex information.
* **1.0x**: Standard natural speed.
* **1.1x - 1.2x**: Brisk, efficient pace for simple queries.

### 4. Filler Words (NEW)

You can toggle "Natural Fillers" to let the agent say things like "Umm," "Got it," or "I see" to bridge gaps in processing time.