Ai Tales Maker
Home
Video
Image
Audio
AI Audio Generator v4 - Professional Edition
Input Type
Plain Text
SSML (Advanced)
SSML allows advanced speech control with tags like <break time="500ms"/> for pauses and <prosody rate="slow"> for speech rate.
Text Content
Story/Text
0 / 450000 characters
Upload .txt File
SSML Quick Tools
Short Pause
Medium Pause
Long Pause
Slow Speech
Fast Speech
Emphasis
Cheerful
Sad
Voice Settings
Gender
Choose gender
Male
Female
Voice
Choose voice
Speaking Style
Default (No Style)
Available styles depend on the selected voice.
Style Intensity
Default (1.0)
Subtle (0.5)
Light (0.8)
Moderate (1.2)
Strong (1.5)
Very Strong (2.0)
Controls the intensity of the speaking style.
Voice Role
Default (No Role)
Available roles depend on the selected voice.
Speech Controls
Speech Rate:
1.0x
0.5x
2.0x
Pitch:
0st
-10st
+10st
Volume:
0dB
-10dB
+10dB
Auto-pause after sentences
No auto-pause
Short (200ms)
Medium (500ms)
Long (1s)
Extra Long (2s)
Audio Format
WAV (24kHz, 16-bit)
MP3 (24kHz, 48kbps)
MP3 (24kHz, 96kbps)
MP3 (48kHz, 96kbps)
MP3 (48kHz, 192kbps)
Advanced Features
Enable Custom Pronunciation
Allows custom pronunciation for specific words.
Generate Viseme Data
For lip-sync applications (experimental).
Generate Audio
Preview SSML
SSML Preview
Generated Audio
Your browser does not support the audio element.
Download Audio
Generate Another
Audio Info
Audio Information:
Format:
Size:
Voice:
Style:
Generated:
Loading...
Generating audio... Please wait.