Resemble AI Releases Chatterbox Turbo for Open TTS
The new text-to-speech model focuses on performance and offers voice cloning capabilities for English under a permissive MIT license.
Resemble AI, a company specializing in synthetic voice technology, has released a new open-source model named Chatterbox Turbo. The model is designed for high-performance text-to-speech (TTS) generation in English, targeting developers who need fast and efficient voice output in their applications.
Beyond standard speech synthesis, Chatterbox Turbo includes voice cloning capabilities, allowing users to create speech in a specific target voice from a short audio sample. The entire project is available on Hugging Face under the permissive MIT license, encouraging wide use and modification in both academic and commercial projects.
This release adds another strong contender to the rapidly growing field of open-source speech generation. While proprietary APIs have dominated the high-quality TTS space, permissively licensed models like Chatterbox Turbo provide a crucial, self-hostable alternative for developers. This move from a commercial provider signals a broader trend of companies contributing foundational models back to the community.
Developers interested in experimenting with the model can find the necessary code and instructions on the official Hugging Face repository.
Sources
- Visit
ResembleAI/chatterbox-turbo
Hugging Face
More from Resemble AI
All Resemble AI releases →
Resemble AI Releases Dramabox Voice Cloning TTS Model
The new text-to-speech model uses a diffusion-transformer architecture for high-quality, expressive audio and one-shot voice cloning.
Moonshine: Open STT Models Aim to Beat Whisper
Resemble AI releases MIT-licensed speech-to-text models that claim higher accuracy than OpenAI's Whisper Large v3.
More in Text → Speech
All Text → Speech →
Liquid AI's LFM3-Omni-2B brings any-to-any AI to the edge
The 2-billion-parameter model combines vision, audio and speech-to-speech in a package small enough to run on device.
IBM's Granite Switch 4.1 Unifies Chat, Logic, Speech
A single endpoint now routes text conversation, decision-making, and speech synthesis across IBM's Apache-licensed Granite line.
Fish Audio's Drama 3 brings MoE to open TTS
The open-source speech model pairs a 35B mixture-of-experts backbone with voice cloning and directed performance control.
0 comments
No comments yet. Be the first to weigh in.