Generate Speech

0 / 8192 characters
English
French
German
Korean
Hindi
Mandarin
Spanish
Italian
Tara
Female, English, conversational, clear
Leah
Female, English, warm, gentle
Jess
Female, English, energetic, youthful
Leo
Male, English, authoritative, deep
Dan
Male, English, friendly, casual
Mia
Female, English, professional, articulate
Zac
Male, English, enthusiastic, dynamic
Zoe
Female, English, calm, soothing
Advanced options
Slower 1.0 Faster

Server Configuration

These settings will be saved to a .env file. Restart the server to apply changes.

Fixed at 1.1
Value hardcoded to 1.1 for optimal generation quality

Supports emotion tags: <laugh>, <sigh>, etc.

Tips & Tricks

  • Use <laugh> to add laughter to the speech
  • Use <sigh> for a sighing sound
  • Other supported tags: <chuckle>, <cough>, <sniffle>, <groan>, <yawn>, <gasp>
  • For longer audio, the system can generate up to 2 minutes of speech in a single request
  • For API access, use the /v1/audio/speech endpoint (OpenAI compatible)