Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
microsoft
/
VibeVoice-1.5B
like
1.93k
Follow
Microsoft
16.1k
Text-to-Speech
Transformers
Safetensors
VibeVoice
English
Chinese
text-generation
Podcast
arxiv:
2508.19205
arxiv:
2412.08635
License:
mit
Model card
Files
Files and versions
xet
Community
40
Train
Deploy
Use this model
e69c699
VibeVoice-1.5B
5.41 GB
5 contributors
History:
15 commits
hululuhu
update README
e69c699
about 2 months ago
figures
update README
about 2 months ago
.gitattributes
Safe
1.6 kB
update README
about 2 months ago
README.md
7.25 kB
update README
about 2 months ago
config.json
Safe
2.76 kB
Upload VibeVoice 1.5B model
about 2 months ago
model-00001-of-00003.safetensors
Safe
1.98 GB
xet
Upload VibeVoice 1.5B model
about 2 months ago
model-00002-of-00003.safetensors
Safe
1.98 GB
xet
Upload VibeVoice 1.5B model
about 2 months ago
model-00003-of-00003.safetensors
Safe
1.45 GB
xet
Upload VibeVoice 1.5B model
about 2 months ago
model.safetensors.index.json
Safe
123 kB
Upload VibeVoice 1.5B model
about 2 months ago
preprocessor_config.json
Safe
351 Bytes
Upload VibeVoice 1.5B model
about 2 months ago
