Bonus: Top up now and we'll double your first deposit — get x2 credits instantly.
Get Started
Sign Up
Sign Up

Deepgram Aura 2

Up to 30%

Synthesize speech with Deepgram Aura 2 on LLM.API—text in, audio out, billed and authenticated like the rest of your model fleet.

Start Using API

What is Deepgram Aura 2?

Deepgram Aura 2 synthesizes spoken audio from text through LLM.API. Text-to-speech model by Deepgram. Use api id `aura-2` with the same key as chat and media models.

Providers

LLM.API routes Deepgram Aura 2 to the providers below, with discounted effective rates versus list price.

ProviderPricingContextCapabilities
deepgram30% offin $30; out — per 1M characters——

Prices and availability from the LLMAPI catalogue, updated nightly. Last updated 21 Sept 2026.

Try this model

Test Deepgram Aura 2 right here — free to start.

Deepgram Aura 2
Hi! Want to test the model?

Suggestions for your first prompt

Code snippet

Call Deepgram Aura 2 through the OpenAI-compatible API — TTS via LLM.API (see docs for audio endpoints).

python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LLMAP_KEY",
    base_url="https://api.llmapi.ai/v1",
)

resp = client.chat.completions.create(
    model="aura-2",
    messages=[
        {"role": "system", "content": "You are a precise product assistant."},
        {"role": "user", "content": "Give me three crisp launch checklist items."},
    ],
)
print(resp.choices[0].message.content)
{
  "model": "aura-2",
  "messages": [
    {"role": "system", "content": "You are a precise product assistant."},
    {"role": "user", "content": "Give me three crisp launch checklist items."}
  ]
}

5 Core Capabilities

  • Voice product UX

    Enables talk-back experiences in apps and devices.

  • Accessibility audio

    Helps create listen-able versions of written content.

  • Promptable delivery

    Responds to punctuation and phrasing cues for pacing. Grounded in the model's tts role rather than generic chat claims.

  • Prototype speed

    Lets teams ship voice demos without recording studios. Grounded in the model's tts role rather than generic chat claims.

  • Natural speech synthesis

    Turns text into spoken audio for assistants, accessibility, and media. Tuned to how teams typically call Deepgram Aura 2.

6 Most Valuable Use Cases

  • Game and app character voice drafts with Deepgram Aura 2
  • Accessibility listen modes for articles
  • IVR prompt generation with Deepgram Aura 2
  • Rapid podcast intro/outro prototypes
  • Alert and notification spoken prompts with Deepgram Aura 2
  • Multilingual demo voiceovers

Why Build on LLM.API?

One unified API. Every major model. Built-in reliability, cost control, and observability.

  • Intelligent AI Routing

    Automatically route each request to the best model across providers based on latency, cost, and quality—without changing your integration or redeploying code.

    One endpoint, every model.

  • Cost-Aware Execution

    Control spend with per-request cost estimation, smart model selection, and centralized quotas so teams can experiment fast without runaway bills or manual tracking.

    More performance, less spend.

  • Resilient Fallback Flows

    Define automatic, provider-agnostic fallbacks to keep your app up during outages, rate limits, or timeouts—no brittle failover logic scattered through your codebase.

    Never go dark on users.

  • Deep LLM Observability

    Trace every call across providers with logs, metrics, and request replay so you can debug, tune prompts, and optimize model choices from one unified dashboard.

    See every token, everywhere.

  • Task-Level Orchestration

    Describe tasks, not models. LLM.API maps them to the right tools, models, and prompts so you ship complex AI workflows with minimal glue code.

    Think tasks, not models.

  • High-Throughput Batch APIs

    Process millions of inferences efficiently with optimized batch pipelines, concurrency controls, and retry logic—all behind the same simple interface you use for single calls.

    Scale from 1 to millions.

Why run Deepgram Aura 2 on LLM.API?

  • Unified AI Routing

    Production: Reach Deepgram Aura 2 and sibling models through one OpenAI-compatible endpoint.

  • Cost Control

    Practical: Compare provider price points and keep spend visible as you scale Deepgram Aura 2.

  • Reliability Layer

    Retry and route across configured providers when a single upstream blips.

  • Observability

    Production: Trace prompts, tokens, and errors for Deepgram Aura 2 alongside the rest of your stack.

  • Drop-in SDKs

    Keep using familiar OpenAI client patterns with base URL https://api.llmapi.ai/v1.

  • Model Breadth

    Practical: Swap Deepgram Aura 2 for chat, media, or embedding alternatives without rewriting auth.

When to Use — When NOT to Use

Use it if...

  • You want API-driven voice prototypes that can go to production (Deepgram Aura 2)
  • You need text-to-speech without managing voice infrastructure (Deepgram Aura 2)
  • Your UX requires spoken responses or narration (Deepgram Aura 2)

Avoid if...

  • You require a specific celebrity voice you do not have rights to
  • You only need embeddings or OCR
  • You need speech recognition rather than synthesis

COMMUNITY

What developers say about text-to-speech models

Summarised from publicly published developer and community reviews of this model family. Opinions are the sources’, not LLM.API’s, and may not be specific to Deepgram Aura 2.

  • Community consensus still puts ElevenLabs-class voices at the top for realism and emotional range.
  • The debate has shifted from quality to value, as open-source voices mature and heavy usage pushes teams to higher tiers.
  • Developers advise designing for rate limits early — 429 handling on generation calls is a common production surprise.

SOURCES

Frequently Asked Questions

  • Does Deepgram Aura 2 support streaming?

    Streaming depends on the active provider; check the providers table on this page for flags.

  • Can I use tools or structured outputs with Deepgram Aura 2?

    Tooling support varies; for pure tts models, prefer the modalities listed rather than assuming chat tools.

  • Which providers serve Deepgram Aura 2?

    LLM.API currently lists: deepgram. Availability can vary by region and account.

  • How do I call Deepgram Aura 2 via API?

    Send OpenAI-compatible requests to https://api.llmapi.ai/v1 with model "aura-2" and your LLM.API key. See the code snippet on this page.

  • What is the context length for Deepgram Aura 2?

    Reported context for Deepgram Aura 2 is See provider specs. Always verify the active provider row if multiple providers are listed.

  • Can I clone any voice with Deepgram Aura 2?

    Only use voices and styles you have rights to. Follow provider and LLM.API acceptable-use rules.

  • What modalities does Deepgram Aura 2 support?

    Deepgram Aura 2 accepts text and produces audio according to its architecture metadata on LLM.API.

  • Where is the canonical page for Deepgram Aura 2?

    https://llmapi.ai/models/aura-2/

  • What are limitations of Deepgram Aura 2?

    Like other API models, Deepgram Aura 2 can be wrong, incomplete, or uneven on edge cases. Validate outputs for high-stakes use. Media/OCR/STT models additionally depend on input quality.

  • When should I choose Deepgram Aura 2?

    You need text-to-speech without managing voice infrastructure — especially when you specifically need Deepgram Aura 2.

  • Is Deepgram Aura 2 a chat model?

    No—Deepgram Aura 2 is categorized as a tts model. Use the matching API surface rather than assuming chat completions.

COMPARE

Competitive Models

Get one key to every model

Swap your API key. Keep your code.

Start for free Talk to sales