YepAPI
AI Models

Deepgram Aura-2

Deepgram's multilingual speech model with the largest voice roster on the platform — 90 named voices.

POST/v1/media/queue
$0.0633/1K chars

Overview

Aura-2 is Deepgram's multilingual text-to-speech model, and it ships the widest voice catalogue of any speech model on YepAPI: 90 named voices spanning English, Spanish, French, German, Italian, Dutch, and Japanese. Pick a voice by its canonical Aura-2 identifier.

PropertyValue
Model IDdeepgram/aura-2
Aliasaura
Upstream Modeldeepgram/aura-2
CategoryText to Speech
LanguagesEnglish, Spanish, French, German, Italian, Dutch, and Japanese
Outputmp3 (default) or pcm
Pricing$0.0633 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: 'deepgram/aura-2',
    prompt: 'Your text to speak goes here.',
    options: { voice: 'aura-2-thalia-en' },
  }),
});
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": "deepgram/aura-2", "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
modelstringYesdeepgram/aura-2
promptstringYesThe text to speak (max 50,000 bytes)
options.voicestringNoVoice identifieraura-2-thalia-en
options.outputFormatstringNomp3 (default) or pcmmp3
options.speednumberNoPlayback speed multiplier. Honoured only by models that support it1.0

Voices

aura-2-thalia-en is used when options.voice is omitted. 90 voices available (10 of 90 shown):

  • aura-2-thalia-en
  • aura-2-apollo-en
  • aura-2-luna-en
  • aura-2-orion-en
  • aura-2-agathe-fr
  • aura-2-alvaro-es
  • aura-2-aurelia-de
  • aura-2-cesare-it
  • aura-2-beatrix-nl
  • aura-2-ama-ja

Features

  • 90 named voices — the largest roster available
  • Seven languages in one model
  • Consistent voice identity across requests
  • Built for contact-centre and assistant workloads

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