New Generation

Text-only voice design, no reference audio required.

Ready

Input

Create speech from text, with or without a reference voice.

0 / 500 characters Estimated 7 sec
Advanced Settings normalization on, guidance 2.0

Output

Preview generated audio and keep successful takes.

Ready to generate. Text-only mode does not require a voice upload.

Current Job

Mode
Text to Speech
Voice
Designed voice
Length
0 characters
Status
Draft