YepAPI
AI Models

Sesame CSM 1B

A conversational speech model that separates conversational delivery from read-aloud delivery.

POST/v1/media/queue
$0.0148/1K chars

Overview

CSM 1B is a conversational speech model from Sesame. Its voice options split along a useful axis: conversational_* voices for dialogue and assistant turns, read_speech_* voices for narration and read-aloud content. At 1B parameters it stays cheap enough for high-volume use.

PropertyValue
Model IDsesame/csm-1b
Aliascsm
Upstream Modelsesame/csm-1b
CategoryText to Speech
LanguagesEnglish
Outputmp3 (default) or pcm
Pricing$0.0148 per 1,000 characters

Usage

All media models use the async job queue. Submit a job, then poll for the result.

Step 1: Submit Job

const res = await fetch('https://api.yepapi.com/v1/media/queue', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'sesame/csm-1b',
    prompt: 'Your text to speak goes here.',
    options: { voice: 'conversational_a' },
  }),
});
const { data } = await res.json();
// data.jobId — use this to poll for results
curl -X POST https://api.yepapi.com/v1/media/queue \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "sesame/csm-1b", "prompt": "Your text to speak goes here."}'

Step 2: Poll for Result

const status = await fetch(`https://api.yepapi.com/v1/media/status/${data.jobId}`, {
  headers: { 'x-api-key': 'YOUR_API_KEY' },
});
const { data: job } = await status.json();
// job.status — "pending" | "processing" | "completed" | "failed"
// job.result.audio — { mimeType, base64 } when completed
curl https://api.yepapi.com/v1/media/status/JOB_ID \
  -H "x-api-key: YOUR_API_KEY"

Write the audio to a file:

import { writeFileSync } from 'node:fs';

writeFileSync('speech.mp3', Buffer.from(job.result.audio.base64, 'base64'));

Request Body

ParameterTypeRequiredDescriptionDefault
modelstringYessesame/csm-1b
promptstringYesThe text to speak (max 50,000 bytes)
options.voicestringNoVoice identifierconversational_a
options.outputFormatstringNomp3 (default) or pcmmp3
options.speednumberNoPlayback speed multiplier. Honoured only by models that support it1.0

Voices

conversational_a is used when options.voice is omitted. 6 voices available:

  • conversational_a
  • conversational_b
  • read_speech_a
  • read_speech_b
  • read_speech_c
  • read_speech_d

Features

  • Distinct conversational and read-aloud voice families
  • Purpose-built for dialogue and assistant turns
  • English-only
  • Small and cheap at 1B parameters

Billing

Speech is billed on the length of the input text, in UTF-8 bytes — for English text one byte is one character. The cost is known before synthesis starts, so the balance check at submit time quotes the exact final charge. Jobs have a $0.01 minimum.

Under the Hood

Powered by OpenRouter's unified speech API.

On this page