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…

🚀 New model available: DeepSeek-V3.1 🚀

ResembleAI logo

ResembleAI/

chatterbox

New model named Chatterbox by Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out.

Public
$10.00 per M characters
ProjectLicense
ResembleAI/chatterbox cover image

Input

Text to convert to speech

Voice ID created on deepinfra. (Default: empty)

You need to login to use this model

Login

Settings

Exaggeration

Exaggeration factor for the speech (Default: 0.25, 0 ≤ exaggeration ≤ 1)

CFG

CFG factor for the speech (Default: 0.5, 0.1 ≤ cfg ≤ 1)

Temperature

Temperature for the speech (Default: 0.7, 0 ≤ temperature ≤ 2)

Seed for the random number generator (Default: empty, 0 ≤ seed ≤ 2147483647)

Output

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

Model Information