Interactive
TTS Demo
Generate emotional speech using the Emotional TTS API. Upload a speaker reference audio and enter text to synthesize.
Backend Required
This demo connects to the TTS backend API. Make sure the backend is running via Docker before testing.
Emotion Control Mode
39 characters
WAV, MP3, FLAC, OGG, M4A — min 5 seconds
Output
Generated audio will appear here
Tips
- Use at least 5 seconds of speaker reference audio
- Longer text may take more time to process
- Try different emotions with the same text
- Vector mode is faster; reference mode is more expressive