Model reference · open weights

csm

csm is an open-weight audio or speech model from sesame, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio sesame 1 variants 151k downloads/mo

Request this model on EU hardware All served models Not on the shared API today — deployed on request.

Specifications

What it is

Maker	sesame
Type	Audio & music
Parameters (lead)	1.6B
Variants	1
Runs with	transformers
Released	2025-03-06
Popularity	151k downloads / month
Likes	2,433
Licence	Open weights

How it works

How audio & music work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Variant	Params	Precision	VRAM	Fits 16 GB	Weights
csm-1b	1.6B	BF16	~3.6 GB	✓	Weights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys csm for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (csm below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="csm" -F file=@audio.mp3

Details

Languages, data & research

Languages

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

HuggingFace — sesame/csm-1b ↗

Want csm on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

Breeze-TTS-2 speecht5_finetuned_iamwille_ig granite-speech-5.0-turboctc-nc audio.cpp minimax_music3_text_encoder MiniMax-Music3 MiniMax-Music3 MiniMax-Music3 All audio & music → Full catalogue →