GitHub radar
Audio8 TTS: A small voice cloning model
Audio8_TTS is a 0.6 billion parameter multilingual text-to-speech model with zero-shot voice cloning capabilities across 11 languages. The model can run on a single CUDA GPU and is hosted on Hugging Face with an Apache 2.0 license.
Audio8_TTS is a multi-lingual text-to-speech model created by Audio8. It is built upon DualAR architecture with 0.6 billion parameters. Using this model, you will be able to synthesize high quality speech in any desired voice from a few seconds of audio. The model is available in 11 different languages such as English, Chinese, Japanese, etc., and many other European languages. Available on Hugging Face with Apache 2.0 license.
Why a vibe-coder should care
If you want your application/agent to speak in your preferred voice all the time, then you can use this model to create your voice, character voices, or even a brand voice with just a few seconds of audio recording. No need for a powerful server!
▌ More finds