AU
Audio8-TTS-Preview-0.6b
Audio8
ID: audio8-tts-preview-06b
open weights·Active·audio speech·Updated Jul 28, 2026
Audio8-TTS-Preview-0.6b is a 601M-parameter text to speech model developed by Audio8. Built on the ArkttsModel architecture using transformers. Supports yue, zh, nl, en, fr, de, it, ja, ko, pl, es language(s). Released on 2026-07-28 with 126 likes and 225 downloads on Hugging Face.
Audio8-TTS-Preview-0.6b
Model Overview
Audio8-TTS-Preview-0.6b is a 601M-parameter text to speech model developed by Audio8. Built on the ArkttsModel architecture. Supports yue, zh, nl, en, fr, de, it, ja, ko, pl, es. Released on 2026-07-28.
📊 Quick Specs
Specification Table
| Specification | Value |
|---|---|
| Parameters | 601M |
| Architecture | ArkttsModel |
| Task | text to speech |
| Modality | text, audio |
| License | APACHE-2.0 |
| Framework | transformers |
| MoE | No |
| Languages | yue, zh, nl, en, fr, de, it, ja, ko, pl, es |
✨ Key Features
- 601M parameters
- Built on ArkttsModel architecture (transformers)
- Primary task: text to speech (text, audio modality)
- Language support: yue, zh, nl, en, fr, de, it, ja, ko, pl, es
- Open-weights under APACHE-2.0 license — self-hostable and fine-tunable
📈 Community Adoption
- 126 likes on Hugging Face
- 225 downloads on Hugging Face
🔗 Resources
- Hugging Face Hub: Audio8-TTS-Preview-0.6b on Hugging Face
📜 License & Access
APACHE-2.0 — Open-weights model available for download, fine-tuning, and self-hosted deployment.
