Edge0 / Audio8 TTS Preview 0.6B
Audio8 TTS
Compact multilingual cloning at 0.6B scale
Windows only
Parameters
0.6B
Languages
11
Output
44.1 kHz
Platform
Windows only
Model overview
Built into OpenVox for private local voice generation.
Audio8 TTS Preview is a compact 0.6B-parameter multilingual speech model with zero-shot voice cloning and a 44.1 kHz neural audio codec.
Audio8 combines a compact 0.6B architecture with multilingual speech generation and zero-shot voice cloning.
The preview release recommends 11 languages: Cantonese, Chinese, Dutch, English, French, German, Italian, Japanese, Korean, Polish, and Spanish.
Its included neural audio codec produces 44.1 kHz speech and handles both reference encoding and waveform decoding.
In OpenVox, Audio8 TTS is available on Windows and runs locally after its model files are downloaded.
OpenVox does not provide celebrity voice models and does not permit cloning, impersonating, or commercially using any person's voice without proper rights or consent.
Open-source model: Edge0 / Audio8 TTS Preview 0.6B
View on Hugging Face