Voice Settings give you precise control over how your agent sounds and listens. From speech speed to background ambiance, pronunciation rules to turn-taking — this is where you shape the audio experience.
Location: Left Sidebar → Agent Settings → Voice tab
Voice
Select the voice for your agent. Click the dropdown to browse available voices — you can preview each one before selecting.
Speech Settings
Speech Speed
Control how fast your agent speaks.
| Control | Range | Default |
|---|
| Slider | Slow ↔ Fast | 1 |
Pronunciation & Background
Pronunciation Dictionaries
Add custom pronunciations for words that aren’t pronounced correctly by the default voice.
This is especially useful for:
- Brand names
- Technical terms
- Proper nouns
- Industry-specific jargon
To add a pronunciation: Click Add Pronunciation to open the modal.
| Field | Description |
|---|
| Word | The word as written |
| Pronunciation | How it should sound |
Background Sound
Add ambient audio behind your agent’s voice for a more natural feel.
| Option | Description |
|---|
| None | Silent background (default) |
| Office | Subtle office ambiance |
| Call Center | Busy call center sounds |
| Static | Light static noise |
| Cafe | Coffee shop atmosphere |
Advanced Voice Settings
Mute User Until First Bot Response
When enabled, the user’s audio is muted until the agent’s first response is complete. Useful for preventing early interruptions during the greeting.
Voicemail Detection
Detects when a call goes to voicemail instead of reaching a live person.
Voicemail detection may not work as expected if Release Time is less than 0.6 seconds.
Personal Info Redaction (PII)
Automatically redacts sensitive personal information from transcripts and logs.
Denoising
Filters out background noise and improves voice clarity before processing. This helps reduce false detections caused by environmental sounds — useful when callers are in noisy environments.
Voice Detection
Fine-tune how your agent recognizes when someone is speaking.
Confidence
Defines how strict the system is when deciding if detected sound is speech.
- Higher values → Less likely to trigger on background noise
- Lower values → More sensitive to quiet speech
Min Volume
The minimum volume level required to register as speech.
Trigger Time (Seconds)
How long the system waits after detecting the start of user speech (and after the bot has finished speaking) before processing. This helps avoid overlapping speech and false triggers.
Release Time (Seconds)
How long the system waits after the user stops speaking before the bot begins its response. This ensures the user has completely finished their thought.
Start with defaults. Only adjust these if you’re experiencing specific issues like missed words or premature responses.
Smart Turn Detection
Intelligent detection of when the caller is done speaking. When enabled, the agent uses context and speech patterns — not just silence — to determine when it’s time to respond.
Interruption Backoff Timer
Time in seconds to prevent interruptions after the bot starts speaking (default: 0, disabled).
This helps prevent conversation loops when the user and bot interrupt each other — the agent will wait this duration before allowing itself to be interrupted again.
