kokoro-82m — AI Audio Model

jaaari

jaaari

kokoro-82m

Commercial useaudio

Kokoro-82M is best for delivering high-quality, multilingual text-to-speech synthesis. It supports multiple voices with different accents, genders, and tones with remarkable speed and efficiency, making it ideal for real-time applications and resource-constrained environments.

Model Type
coin

Pricing: 0.3 joules / second

Input
speed
Speech speed multiplier (0.5 = half speed, 2.0 = double speed)
0.15.0

voice

Voice to use for synthesis

OutputAUDIO

Output will be displayed here

Fill in the inputs on the left and hit RUN to preview the results.

Examples

Explore different use cases and parameter configurations