models/Deepgram/Aura-2-EN
Deepgram

Aura-2-EN

audio-tts
Compare

Aura-2 is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output.

MODALITIES
audio
RELEASED
2025-10-09

Aura-2-EN (deepgram/aura-2-en) is a audio-tts model from Deepgram, released 2025-10-09. Pricing via AIgateway: $0.030 per 1K chars. Capabilities: streaming, async. Call it via https://api.aigateway.sh/v1/audio/speech — set model="deepgram/aura-2-en". Best for: Voice agents, IVR, Audiobook narration.

model · deepgram/aura-2-enfamily · Aura

Use this model

model: deepgram/aura-2-en
curl https://api.aigateway.sh/v1/audio/speech \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepgram/aura-2-en","voice":"alloy","input":"Hello, world."}'

Capabilities

StreamingAsync

Strengths

  • Natural prosody
  • Real-time streaming
  • Cheap

Use cases

Voice agentsIVRAudiobook narration

Pricing

Per 1K chars$0.030
Streaming SSE at <400ms first-byte
You pay pass-through · 5% applied at credit top-up, not per-call.
See API example →CompareAPI referenceSee usage ranking →

Collections

More audio models →More from Deepgram →Frontier models →Free-tier models →
API schema

Call Aura-2-EN from any OpenAI SDK

POST https://api.aigateway.sh/v1/audio/speech·Content-Type: application/json·Auth: Bearer sk-aig-...

Request body

json
{
  "model": "deepgram/aura-2-en",
  "input": "Hello from AIgateway.",
  "voice": "alloy",
  "format": "mp3",        // mp3 | wav | flac | opus
  "speed": 1.0
}

Response

json
// Binary audio stream in the requested format (mp3 by default).
// Content-Type: audio/mpeg  (or audio/wav, audio/flac, audio/opus)
// Read the response body directly to a file.

Quickstart

from openai import OpenAI
client = OpenAI(base_url="https://api.aigateway.sh/v1", api_key="sk-aig-...")

r = client.audio.speech.create(model="deepgram/aura-2-en", voice="alloy", input="Hello world.")
r.stream_to_file("out.mp3")

Errors

401authentication_errorInvalid or missing API key
402insufficient_creditsWallet empty (PAYG only)
404not_foundUnknown model or endpoint
429rate_limit_errorOver per-minute limit — see Retry-After header
500server_errorUpstream provider failed (retryable)
503service_unavailableUpstream saturated (retryable)
Full docs →API reference →OpenAPI spec →llms.txt →

Frequently asked questions

What is Aura-2-EN?
Aura-2 is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output. It is a audio-tts model from Deepgram, accessible via AIgateway's OpenAI-compatible API at slug deepgram/aura-2-en.
How much does Aura-2-EN cost via AIgateway?
Pass-through pricing plus a 5% platform fee applied at top-up. See the pricing panel on this page for exact rates.
How do I call Aura-2-EN from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to "deepgram/aura-2-en". The request and response shapes match OpenAI exactly.
Does Aura-2-EN support streaming, tool calling, vision, and JSON mode?
Streaming — yes. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.
What are the best use cases for Aura-2-EN?
Voice agents, IVR, Audiobook narration. Key strengths: Natural prosody; Real-time streaming; Cheap.
Can I bring my own Deepgram API key (BYOK)?
Yes. Attach a Deepgram key in your AIgateway dashboard and this model flips to pass-through — you pay Deepgram directly and AIgateway waives the 5% platform fee on those calls.