Home
Voices Library
Playground
Text to Speech
Speech to Text
Audio Narrative
Studio
Beta
Tools
Voice Cloning
Voice Isolation
Translation
Dubbing
New
Image & Video
New
Sound Effects
New
Developer
API Keys
Documentation
Voice Cloning
Feedback
Docs
Try Our AI Agents
Voice Sample
Upload or Drag and drop voice here
Max file size: 20MB, Max duration is 60 seconds
Record a voice
Recording should be clear and less than 60 seconds
Preview Text
Try a sample
Dramatic Scene
News Reader
Casual Speaking
Podcast Mode
Different Languages
Documentary
Reading a Story
0/500 characters
Generate Preview
Settings
History
Cloned Voices
Model
Faseeh V1
Dialect
MSA (Fusha)
Stability
50%
Low (creative)
High (recommended)
Lower is better for English and neutral voices. Higher is better for Arabic and more expressive, emotional voices.
Voice Cloning | Munsit
