OpenMOSS streaming speech model for context-aware, multi-turn voice agents, with Arabic (ar) and voice cloning. Public downloadable weights; no hosted Hugging Face Inference Provider. Apache-2.0 in GitHub and model metadata. Official language counts differ; Arabic is confirmed. Arabic audio quality not tested by Souq.
- Category
- Voice & speech
- Type
- MODEL
- Country / maker
- OpenMOSS
- Pricing
- Free
- Announced
- 10 Feb 2026
- Item last updated
- Not documented yet
- Added to Souq
- 13 Nov 2026
A native speaker reviewed the Arabic description, and the capabilities and languages were checked by hand and approved by the Souq team.
Official links
Official website — github.com (opens in a new tab on github.com)Related tools
© 2026 Souq. Original text and design: all rights reserved. Third-party trademarks and source material belong to their respective owners.