Downloads · 30 days
8
11% of all-time downloads
osirissound-tts
osirisbrain/osirissound-tts
osirissound-tts is a text-to-speech model from osirisbrain. Use it when you need text read aloud. The card lists the license as apache-2.0.
Ultra-fast text-to-speech engine for OsirisBrain AGI. 82M parameters, 9 languages, 55 voice packs.
All-time downloads
72
Public
Repo size
356 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth327 MB · 92%
At a glance
- Task
- Text-to-Speech
- License
- apache-2.0
- Access
- Public
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026
- SHA
- 01de6f70
Model card
From the Hugging Face model README
OsirisSound TTS — Sovereign Voice Engine
Ultra-fast text-to-speech engine for OsirisBrain AGI. 82M parameters, 9 languages, 55 voice packs.
Features
- ~0.5-3s synthesis on Apple Silicon
- 9 Languages: English (US/UK), Spanish, French, Hindi, Italian, Japanese, Portuguese (BR), Chinese
- 55 Voice Packs including custom Osiris blend
- 100% Local — No cloud, no API keys, no external connections
Model
osirissound-v1.pth— OsirisSound TTS v1.0 weights (82M params)
Voices
voices/osiris.pt— Custom blended voice (onyx50+michael30+george20)- 54 standard voice packs across 9 languages
License
Apache 2.0
- Task
- Text-to-Speech
- License
- apache-2.0
- Languages
- en, es, fr, ja, zh, hi
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026