✦
Summary
Audio8 TTS Preview 0.1B is a compact zero-shot text-to-speech model for speech generation and voice cloning. Its main generative model is approximately 170 million parameters, with a separate codec decoder, making the full stack much smaller than many multilingual TTS systems.
Key Features
Approximately 170M-parameter main model.
Zero-shot voice cloning.
Text-to-speech generation.
Slow and fast autoregressive branches.
Bundled neural audio codec.
Chinese and English primary support.
Seven additional experimental languages.
ONNX INT8 CPU deployment option.
About Audio8 TTS Preview 0.1B
The Audio8 Falcon H1 architecture uses slow and fast autoregressive branches: the slow branch predicts semantic tokens, while the fast branch predicts codec codebooks conditioned on the slow hidden state. The bundled codec, tokenizer, processor, and remote code support Hugging Face Transformers inference and CPU deployment through ONNX INT8.
Chinese and English are the primary languages, with experimental evaluation in German, Spanish, French, Italian, Japanese, and Korean. Audio8 is useful for lightweight narration, voice prototyping, localization, and privacy-conscious local speech workflows, subject to consent and license requirements for voice cloning.