Instructions to use microsoft/VibeVoice-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/VibeVoice-1.5B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="microsoft/VibeVoice-1.5B")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("microsoft/VibeVoice-1.5B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
VibeVoice β mobile TTS with emotion, finally
#52
by 3morixd - opened
1.5B params for TTS with emotion control? This is exactly what mobile needs.
We're testing VibeVoice on our phone farm. The quality is remarkable β natural prosody, emotion control, and it fits in 1GB (quantized).
Use case: mobile apps that read text aloud with appropriate emotion β children's stories, news, accessibility.
Microsoft has been quietly releasing some of the best small models. VibeVoice is a gem.
β Dispatch AI (FZE), Sharjah UAE