🚀 New model available: DeepSeek-V3.1 🚀
ResembleAI/
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.
Text to convert to speech
Voice ID created on deepinfra. (Default: empty)
You need to login to use this model
LoginSettings
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)
Waiting for audio data... Submit request to start streaming.
© 2025 Deep Infra. All rights reserved.