csm-1b
CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.
text → audio · made by sesame
$0.3→$1.2per Mtok in / out
Featherless AI · 2 sellers
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| Featherless AI aggregator | standard | $0.3per Mtok in$1.2per Mtok outapi.featherless.ai · read 2026-09-20 |
| DeepInfra aggregator | standard | $7per million charactersapi.deepinfra.com · read 2026-08-25 |
About
csm-1b — an audio model from sesame, sold by 2 companies from $0.3 in and $1.2 out per million tokens.
It takes text and returns audio. The catalogue files it under speak. Two companies sell it. The cheapest is $0.3 in and $1.2 out per million tokens at Featherless AI.
Every current figure
- Maker
- sesame
- Register
- model
- Takes
- text
- Returns
- audio
- Parameters
- 1 billion · read from its own name
- Licence
- not read
- Sellers
- 2
- Maker's own price
- not read
- Price
- $0.3 in and $1.2 out per million tokens — Featherless AI
Known as 1 name
sesame/csm-1b