KOTA Text-to-Speech
Generate natural speech from text using Kokoro-FastAPI TTS models.
Home
›
Text-to-Speech
Text Input
Text to Speak
*
0 / 5000
Voice
af_bella - Professional, articulate
af_heart - Warm, conversational (default)
af_nicole - Energetic, youthful
af_sarah - Calm, soothing
af_sky - Bright, cheerful
af_alloy - Versatile
af_echo - Resonant
af_fable - Storytelling
af_nova - Modern
af_shimmer - Bright
am_adam - Deep, authoritative
am_michael - Friendly, casual
am_echo - Resonant
am_fable - Storytelling
am_onyx - Deep
bf_emma - Refined, articulate
bf_isabella - Elegant, sophisticated
bf_alloy - Versatile
bf_nova - Modern
bf_shimmer - Bright
bm_george - Distinguished, formal
bm_lewis - Casual, contemporary
bm_alloy - Versatile
bm_echo - Resonant
bm_onyx - Deep
bm_shimmer - Bright
Speed
1.0x
Speak
Clear
Generated Speech