⚙️ Enhancement Model Settings
×
Select AI Model for Text Enhancement
(Loading...)
Loading models...
ℹ️ Info:
The selected model will enhance your text with audio tags like [laughing], [sighs], etc. for more expressive speech generation.
Dashboard
>
Speech Generation
🎤 Text-to-Speech Generator
Generate high-quality speech using ElevenLabs AI
Speech Configuration
Text to Speech
Enter any text to convert to natural-sounding speech
✨🪄✨ Enhance Text
Voice
Default Voice
Model
v3 - Most Expressive (Alpha)
Flash v2.5 - Ultra Fast (~75ms)
Turbo v2.5 - Balanced Quality/Speed
Multilingual v2 - High Quality
Turbo v2
Monolingual v1 (Deprecated)
Output Format
MP3 44.1kHz 128kbps
MP3 22.05kHz 32kbps
PCM 16kHz
PCM 22.05kHz
PCM 24kHz
PCM 44.1kHz
Text Normalization
Auto
On
Off
Voice Settings
Stability
0.5
Higher values make the voice more stable but less expressive
Similarity Boost
1.0
Enhances similarity to the original voice
Style
0.0
Controls the style and emotion of the voice
Speed
1.0
Controls the speaking speed (1.0 = normal, 0.7-1.2 range)
Use Speaker Boost
Enhances the speaker's characteristics
Generate Speech
Generated Speech
Your browser does not support the audio element.
Download Audio
Play Again
Quick Examples
Greeting
Announcement
Narration
Custom Message