Deepfake Generator

Voice Cloning

Generate Voice Model

Record Voice Sample

Model Title

Output

Generate Text to Speech (TTS)

Select Model

Select a model to use for TTS

Text for TTS

Text for generated speech. You can add special effects to enhance the result: (break), (long-break), (breath), (laugh), (cough), (lip-smacking), (sigh)

TTS Output

Avatar Creation

Upload Image

Aspect Ratio

1:1 16:9 9:16

Resolution

540p 720p

(Optional) Text Prompt

Influence the expressivity of generated avatar

(Optional) Seed for generation

1 10000

Talking Head