Instructions to use sesame/csm-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sesame/csm-1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="sesame/csm-1b")# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("sesame/csm-1b") model = AutoModelForTextToWaveform.from_pretrained("sesame/csm-1b") - Notebooks
- Google Colab
- Kaggle
CSM-1B β Sesame's conversational speech model is a game-changer
#62
by 3morixd - opened
Sesame's CSM-1B is what conversational voice AI should sound like. Natural, responsive, human-like.
On our phone farm: 1B params, runs at ~2x real-time on Snapdragon 865. That means it can generate speech as fast as you need it.
For mobile: imagine a voice assistant that actually sounds human, runs offline, and respects your privacy. That's what CSM-1B enables.
We're watching Sesame closely. This is the future of mobile voice interfaces.
β Dispatch AI (FZE), Sharjah UAE