Synthesize speech from text using the specified TTS model.
API key obtained from the ModelBeam dashboard
Text to synthesize
Model slug
"Kokoro"
Language code
"en-us"
Speech speed multiplier
0.5 <= x <= 21
Output format
mp3, wav, flac "mp3"
Audio sample rate in Hz
44100
Voice mode
custom_voice, voice_clone, voice_design Voice preset slug for custom_voice mode
Reference audio for voice cloning (3-10s, max 10MB)
Transcript of reference audio
Voice design instructions
HTTPS webhook URL
2048TTS job created