Emotions
Wrap your text in specific emotion tags to guide the tone of the generation.
Vox interprets these parameters as guidance instead of as strict adjustments to ensure natural speech, so we recommend testing them against your content to ensure the output matches your expectations.
| Emotion | Syntax |
|---|
| Netural | Text here |
| Angry | <angry>Text here</angry> |
| Shouting | <shouting>Text here</shouting> |
| Laughing | <laughing>Text here</laughing> |
| Sad | <sad>Text here</sad> |
| Whisper | <whisper>Text here</whisper> |
| Excited | <excited>Text here</excited> |
| Confused | <confused>Text here</confused> |
For netural emotion, don’t place any tag around the text.
The tag should wrap the entire sentence, not just part of it.
Wrong ❌: - I'm <angry>so frustrated with this delay</angry> right now.
Correct ✅: - <angry>I'm so frustrated with this delay right now.</angry>
<angry>I told you specifically not to touch that!</angry>
<whisper>Don't make a sound, they might hear us.</whisper>
<excited>I can't believe we actually won!</excited>
<sad>It's hard to say goodbye after all this time.</sad>
Nonverbalisms
Insert specific non-speech sounds into the transcript using these standalone tags.
| Sound | Tag |
|---|
| Cough | <cough> |
| Yawn | <yawn> |
| Sniffle | <sniffle> |
| Sigh | <sigh> |
I think <cough> I'm coming down with a cold.
Alright <sigh>, let's try this one more time.
It's just so beautiful... <sniffle>
I stayed up way too <yawn> late last night.
Speed Control
Control the pacing of specific sections by wrapping the text in speed tags.
| Speed | Syntax |
|---|
| Slow | <slow>Text here</slow> |
| Fast | <fast>Text here</fast> |
<slow>The secret code is... A... B... C...</slow>
<fast>Terms and conditions apply void where prohibited.</fast>
Need Help?
If you have any questions or need assistance, please contact our support team at support@timepay.ai.
