Text to speech · Sesame
CSM 1B
Conversational speech model that conditions on dialogue context.
Datasheet
Maker | Sesame |
|---|---|
Parameters | 1.55 BVerifiedsafetensors.total from the HF API Source |
Licence | Apache-2.0Verified |
Access | Gated: accept the terms on Hugging Face to download |
Task (HF pipeline) | text-to-speech |
First published on HF | 2025-03-06 |
Last updated on HF | 2025-12-01 |
Weights in memory | 3.1 GB at 16-bit · 0.9 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build. |
Benchmark
Not yet measured
No common public benchmark captured yet
No comparable public score for this benchmark yet. We will not estimate one.
The description summarises the model card at https://huggingface.co/sesame/csm-1b. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.