We use essential cookies to make our site work. With your consent, we may also use non-essential cookies to improve user experience and analyze website traffic…

hexgrad/

Kokoro-82M

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects.

Public
$0.62 per M characters
ProjectPaperLicense
hexgrad/Kokoro-82M cover image

Input

Text to convert to speech

Settings

Select the desired format for the speech output. Supported formats include mp3, opus, flac, wav, and pcm. 5

af_bella

Select the desired voice for the speech output. You can select multiple to combine and mix voices.

Speed of the speech (Default: empty, 0.25 ≤ speed ≤ 4)

Whether to stream the output 2

Whether to return timestamps 2

Sample rate for the output audio. (Default: empty)

Minimum number of tokens for the output. (Default: empty)

Maximum number of tokens for the output. (Default: empty)

Absolute maximum number of tokens for the output. (Default: empty)

Output

Waiting for audio data... Submit request to start streaming.

Model Information

Unlock the most affordable AI hosting

Run models at scale with our fully managed GPU infrastructure, delivering enterprise-grade uptime at the industry's best rates.