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.
Aura-2-ES (deepgram/aura-2-es) is a audio-tts model from Deepgram, released 2025-10-09. Pricing via AIgateway: $0.012 per 1K chars. Capabilities: streaming, async. Call it via https://api.aigateway.sh/v1/audio/speech — set model="deepgram/aura-2-es".
curl https://api.aigateway.sh/v1/audio/speech \
-H "Authorization: Bearer $AIGATEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepgram/aura-2-es","voice":"alloy","input":"Hello, world."}'{
"model": "deepgram/aura-2-es",
"input": "Hello from AIgateway.",
"voice": "alloy",
"format": "mp3", // mp3 | wav | flac | opus
"speed": 1.0
}// 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.
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-es", voice="alloy", input="Hello world.")
r.stream_to_file("out.mp3")