Kani-TTS-2 Offers New Open-Source Voice Generation
An independent researcher has released a new English text-to-speech model under a permissive license, built on a modern generative foundation.
A new, permissively licensed text-to-speech (TTS) model called Kani-TTS-2 has been released by the independent researcher known as 'nineninesix'. The English-language model is now available for download and use on the Hugging Face Hub, providing another option for developers seeking open-source voice generation tools.
Technically, Kani-TTS-2 is built on a Latent Flow Matching 2 (LFM2) backbone. This positions the model within a modern class of generative techniques that aim for efficient and high-quality synthesis. While specific performance benchmarks were not provided with the release, its foundation suggests a contemporary approach to audio generation.
Why It Matters
The release of Kani-TTS-2 contributes to a growing ecosystem of open audio models. With its Apache 2.0 license, developers can freely use, modify, and integrate the model into both research and commercial applications. This stands in contrast to the many proprietary, API-gated TTS services, offering greater flexibility and control for building voice-enabled products.
You can explore the model, listen to samples, and find implementation details in the official Kani-TTS-2 repository on Hugging Face.
Sources
- Visit
nineninesix/kani-tts-2-en
Hugging Face
More from nineninesix
All nineninesix releases →
Gepard 1.0 brings bilingual TTS with voice cloning
An open, autoregressive text-to-speech model targets English and Spanish under a permissive Apache 2.0 license.
Kani TTS 370M Offers Compact Multilingual Speech
Based on the Language-Free Modeling for Multilingual Text-To-Speech (LFM2) architecture, the new model offers an efficient solution for developers.
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.