Voice Providers
Retone supports two premium TTS providers:- Cartesia (Recommended)
- ElevenLabs
Cartesia Sonic 3 offers:
- Ultra-low latency (< 100ms)
- Emotional expressiveness
- Natural prosody
- Speed and stability controls
Basic Settings
Voice Selection
Choose from available voices:- Click the Voice dropdown
- Browse available voices by provider
- Preview voices before selecting
- Click to apply
Speed
Control speaking rate:| Value | Effect |
|---|---|
| 0.5 | Half speed (very slow) |
| 0.8 | Slightly slower |
| 1.0 | Normal speed |
| 1.2 | Slightly faster |
| 2.0 | Double speed (very fast) |
Volume
Output volume level (0-100):Responsiveness
How quickly the agent starts speaking (1-10):| Value | Effect |
|---|---|
| 1-3 | Slower, more deliberate responses |
| 4-6 | Balanced (recommended) |
| 7-10 | Faster, may interrupt caller |
Emotional Expression (Cartesia)
Cartesia Sonic 3 supports emotional speech:Emotion Types
| Emotion | When to Use |
|---|---|
neutral | Professional, business contexts |
friendly | Customer service, general conversations |
excited | Sales, promotions, positive news |
sympathetic | Handling complaints, showing empathy |
curious | Asking questions, gathering information |
confident | Assertions, recommendations |
Intensity
| Level | Effect |
|---|---|
low | Subtle emotional undertone |
medium | Noticeable but not exaggerated |
high | Strong emotional expression |
Back-channeling
Natural acknowledgment sounds during conversation:When Back-channeling Triggers
- During caller’s longer statements
- At natural pauses
- When caller shares information
- To indicate active listening
Higher frequency (7-10) sounds very engaged but may feel excessive. Lower (1-3) is more subtle.
Pre-response Phrases
Filler phrases before AI generates a response:Benefits
- Reduces perceived latency
- Sounds more natural
- Gives AI processing time
Conditional Pre-responses
Trigger different phrases based on context:Laughter Injection
Add natural laughter to appropriate moments:Pronunciation Overrides
Custom pronunciations for specific words:Adding Pronunciations
- Go to Voice Settings
- Click Pronunciation Overrides
- Add word and phonetic spelling
- Test with voice preview
Auto-enabled Features
These settings are enabled by default:| Feature | Description |
|---|---|
| Allow interruptions | Caller can interrupt agent |
| Speech normalization | Numbers read naturally |
| Noise filtering | Background noise reduced |
| Background speech detection | Handles side conversations |
Configuration Example
Complete voice configuration:Testing Voice Settings
- Open the Test Call panel
- Have a conversation with your agent
- Listen for:
- Natural pacing
- Clear pronunciation
- Appropriate emotion
- Smooth back-channeling
- Adjust settings and retest
Best Practices
Match Brand Voice
Choose a voice that fits your company’s personality.
Test on Phone
Audio sounds different on phone vs. computer. Test both.
Moderate Back-channeling
Too much feels robotic; too little feels distant.
Add Key Pronunciations
Ensure company names, products, and jargon sound correct.
Related
System Prompt
Define agent personality
Environment
Background sounds and ambience
Test Call
Test voice settings