# Sesame CSM

> CSM-1B (released March 2025) generates speech as Mimi audio codes from text and optional audio context, using a Llama backbone. Code and CSM-1B weights are Apache-2.0, but the README requires a CUDA GPU and access to two gated Hugging Face repos, including meta-llama/Llama-3.2-1B (Llama 3.2 Community License) for the tokenizer. It ships no preset voices, is mainly English, and cannot generate text. Repo last pushed May 2025.

- Repository: https://github.com/SesameAILabs/csm
- Official docs: https://github.com/SesameAILabs/csm#readme
- Checked: 2026-10-15

## What it replaces
- ElevenLabs: Speech generation (partial). Base model with no fine-tuned voices; README says non-English output likely won't do well.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, Python code runs the model on your own machine | https://github.com/SesameAILabs/csm#usage | 2026-10-15 |
| Code licence | Confirmed | Apache-2.0 | https://github.com/SesameAILabs/csm/blob/main/LICENSE | 2026-10-15 |
| Model weights licence | Partial | CSM-1B weights Apache-2.0 (gated: accept conditions on Hugging Face); the code also loads the tokenizer from meta-llama/Llama-3.2-1B, a manually gated repo under the Llama 3.2 Community License | https://huggingface.co/sesame/csm-1b | 2026-10-15 |
| Commercial use | Partial | Apache-2.0 code and CSM weights allow it, but the required Llama 3.2 tokenizer is under the Llama 3.2 Community License (extra terms, e.g. a separate licence above 700M monthly active users), and the README describes the project as for research and educational purposes with listed prohibited uses | https://raw.githubusercontent.com/meta-llama/llama-models/main/models/llama3_2/LICENSE | 2026-10-15 |
| Paid services needed? | Confirmed | None required; a free Hugging Face account with access granted to CSM-1B and Llama-3.2-1B is needed | https://github.com/SesameAILabs/csm#requirements | 2026-10-15 |
| Hardware | Partial | README lists a CUDA-compatible GPU as a requirement; VRAM and RAM amounts are not stated (example code also selects MPS or CPU if no CUDA) | https://github.com/SesameAILabs/csm#requirements | 2026-10-15 |
| Operating systems | Partial | Windows setup notes given (use triton-windows); Linux and macOS are not explicitly stated | https://github.com/SesameAILabs/csm#windows-setup | 2026-10-15 |
| Setup effort | Confirmed | Medium; git clone, Python 3.10 venv, pip requirements, CUDA, Hugging Face login for gated models | https://github.com/SesameAILabs/csm#setup | 2026-10-15 |

GitHub: 14730 stars, 1478 forks, last push 2025-05-27, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/sesame-csm). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.