YepAPI
AI Models

Orpheus 3B

Canopy Labs' English model, fine-tuned for natural prosody and expressive delivery.

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

Overview

Orpheus 3B is an English text-to-speech model from Canopy Labs, fine-tuned for natural prosody and expressive delivery. Seven preset voices cover narration, voice assistants, and character work at a fraction of the cost of the premium tiers.

PropertyValue
Model IDcanopylabs/orpheus-3b
Aliasorpheus
Upstream Modelcanopylabs/orpheus-3b-0.1-ft
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: 'canopylabs/orpheus-3b',
    prompt: 'Your text to speak goes here.',
    options: { voice: 'tara' },
  }),
});
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": "canopylabs/orpheus-3b", "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
modelstringYescanopylabs/orpheus-3b
promptstringYesThe text to speak (max 50,000 bytes)
options.voicestringNoVoice identifiertara
options.outputFormatstringNomp3 (default) or pcmmp3
options.speednumberNoPlayback speed multiplier. Honoured only by models that support it1.0

Voices

tara is used when options.voice is omitted. 7 voices available:

  • tara
  • leah
  • jess
  • leo
  • dan
  • mia
  • zac

Features

  • Fine-tuned for natural prosody
  • Seven preset voices
  • English-only
  • Roughly half the cost of the mid-tier models

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