Sesame: CSM 1B

CSM 1B is a conversational speech model from Sesame. It accepts text input and produces English speech output, with voice options spanning conversational and read-speech styles. At 1B parameters, it …

sesame/csm-1b

CSM 1B is a conversational speech model from Sesame. It accepts text input and produces English speech output, with voice options spanning conversational and read-speech styles. At 1B parameters, it is suited for dialogue-oriented applications such as voice assistants and interactive agents.

Specifications & capabilities

Input
text
Output
speech
Context window · tokens
4096
Supported voices
conversational_a, conversational_b, read_speech_a, read_speech_b, read_speech_c, read_speech_d, none
Capabilities
speechOutput
Description source ↗

Published prices

1–1 / 1

sesame/csm-1b ↗

$7.00

Inference provider
openRouter
Platform
OpenRouter
Unit
characters_per_million
Currency
USD
Billing conditions
direction
input
Billing label
Input characters (per 1M)

Source specification observations

1–2 / 2

openRouter ↗

field
context_length
value
4096
normalized value
4096
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
3686
normalized value
3686
scope
source-model
source id
openRouter
confidence
1

Original sources

1–4 / 4

DeepInfra · Model page ↗

OpenRouter · Model page ↗

DeepInfra · Catalog ↗

OpenRouter · Catalog ↗

Source links

1–2 / 2

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace