🎙️ Viterbox TTS

Vietnamese & English Text-to-Speech

🎯 Fine-tuned Model

📝 Text Input

Language

🇻🇳 Tiếng Việt 🇺🇸 English

Text to Synthesize

🎤 Reference Voice

Select Voice

Or Upload/Record

⚙️ Settings

Exaggeration

Expression

0 2

CFG Weight

Voice adherence

0 1

Temperature

Variation

0.1 1

Sentence Pause (s)

Pause between sentences

0 2

🔈 Output

Generated Speech

Status

Developed by contextbox.tech

Nguyen Dinh Thuan — boyphuthien115@gmail.com

Nguyen Vinh Huy — nguyenvinhhuy@dtu.edu.vn