Downloads · 30 days
12
6% of all-time downloads
AVoice-TTS
Hak5/AVoice-TTS
AVoice-TTS is a text-to-speech model from Hak5. Use it when you need text read aloud. The card lists the license as gpl-2.0.
Open source Armenian text-to-speech checkpoint for AVoice.
All-time downloads
201
Public
Parameters
613M
3.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors3.3 GB · 100%
Parameter types
How the weights are stored.
F32613M · 100%
Model card
From the Hugging Face model README
AVoice-TTS
Open source Armenian text-to-speech checkpoint for AVoice.
Runtime code:
https://github.com/Hakob-Harutyunyan/AVoice
Usage
Try it in Kaggle! https://www.kaggle.com/code/hakdevelopment/avoice-testing
git clone https://github.com/Hakob-Harutyunyan/AVoice.git
cd Avoice
pip install -U pip
pip install -e .
omnivoice-infer \
--model Hak5/AVoice-TTS \
--text "Բարեւ աշխարհ։" \
--language hy \
--duration 4 \
--output sample.wav
Docker
docker build -t avoice-api https://github.com/Hakob-Harutyunyan/AVoice.git
docker run --gpus all --rm -p 8000:8000 \
-e OMNIVOICE_MODEL=Hak5/AVoice-TTS \
-e OMNIVOICE_DEVICE=cuda \
avoice-api
- Task
- Text-to-Speech
- Type
- omnivoice
- License
- gpl-2.0
- Languages
- hy
- Created
- Apr 30, 2026
- Updated
- May 2, 2026