YourTTS Studio
High-speed multilingual voice cloning & synthesis
Input
0 chars
Text to Speak
Hello! I am YourTTS, a fast and efficient text-to-speech model. I can speak many languages and clone voices instantly.
Voice Source
Upload (Clone)
Saved Voices
Reference Audio (WAV/MP3)
Upload a short clear audio clip (3-10s) to clone the voice.
Loading speakers...
Select from previously saved speakers.
Settings
Language
🇬🇧 English (en)
🇫🇷 French (fr)
🇧🇷 Portuguese (pt)
🇪🇸 Spanish (es)
🇩🇪 German (de)
🇮🇹 Italian (it)
🇵🇱 Polish (pl)
🇹🇷 Turkish (tr)
🇷🇺 Russian (ru)
🇳🇱 Dutch (nl)
🇨🇿 Czech (cs)
🇸🇦 Arabic (ar)
🇨🇳 Chinese (zh-cn)
🇯🇵 Japanese (ja)
🇰🇷 Korean (ko)
ðŸ‡ðŸ‡º Hungarian (hu)
Speed:
1.0
x
Split Long Sentences
Output
Ready
Generate Audio
Logs