Deepgram Aura (Legacy)
Up to 30%Synthesize speech with Deepgram Aura (Legacy) on LLM.API—text in, audio out, billed and authenticated like the rest of your model fleet.
What is Deepgram Aura (Legacy)?
Deepgram Aura (Legacy) synthesizes spoken audio from text through LLM.API. Text-to-speech model by Deepgram. Use api id `aura` with the same key as chat and media models.
Providers
LLM.API routes Deepgram Aura (Legacy) to the providers below, with discounted effective rates versus list price.
| Provider | Pricing | Context | Capabilities |
|---|---|---|---|
| in $15; out — per 1M characters | — | — |
Prices and availability from the LLMAPI catalogue, updated nightly. Last updated 21 Sept 2026.
Try this model
Test Deepgram Aura (Legacy) right here — free to start.
Suggestions for your first prompt
Code snippet
Call Deepgram Aura (Legacy) through the OpenAI-compatible API — TTS via LLM.API (see docs for audio endpoints).
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",
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",
"messages": [
{"role": "system", "content": "You are a precise product assistant."},
{"role": "user", "content": "Give me three crisp launch checklist items."}
]
}5 Core Capabilities
Promptable delivery
Responds to punctuation and phrasing cues for pacing. Tuned to how teams typically call Deepgram Aura (Legacy).
Prototype speed
Lets teams ship voice demos without recording studios. Tuned to how teams typically call Deepgram Aura (Legacy).
Voice product UX
Enables talk-back experiences in apps and devices. Relevant for `aura` workloads on LLM.API.
IVR and alerts
Generates spoken prompts for support and notification flows. 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. Relevant for `aura` workloads on LLM.API.
6 Most Valuable Use Cases
- Accessibility listen modes for articles with Deepgram Aura (Legacy)
- Alert and notification spoken prompts
- Game and app character voice drafts with Deepgram Aura (Legacy)
- Rapid podcast intro/outro prototypes
- Course and help-center narration with Deepgram Aura (Legacy)
- Voice assistants and talk-back UIs
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 (Legacy) on LLM.API?
Unified AI Routing
Reach Deepgram Aura (Legacy) and sibling models through one OpenAI-compatible endpoint.
Cost Control
Compare provider price points and keep spend visible as you scale Deepgram Aura (Legacy).
Reliability Layer
Retry and route across configured providers when a single upstream blips.
Observability
Production: Trace prompts, tokens, and errors for Deepgram Aura (Legacy) 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
Swap Deepgram Aura (Legacy) for chat, media, or embedding alternatives without rewriting auth.
When to Use — When NOT to Use
Use it if...
- Your UX requires spoken responses or narration (Deepgram Aura (Legacy))
- You need text-to-speech without managing voice infrastructure (Deepgram Aura (Legacy))
- You want API-driven voice prototypes that can go to production (Deepgram Aura (Legacy))
Avoid if...
- You need speech recognition rather than synthesis
- You require a specific celebrity voice you do not have rights to
- You only need embeddings or OCR
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 (Legacy).
- 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
Can I clone any voice with Deepgram Aura (Legacy)?
Only use voices and styles you have rights to. Follow provider and LLM.API acceptable-use rules.
What are limitations of Deepgram Aura (Legacy)?
Like other API models, Deepgram Aura (Legacy) can be wrong, incomplete, or uneven on edge cases. Validate outputs for high-stakes use. Media/OCR/STT models additionally depend on input quality.
What modalities does Deepgram Aura (Legacy) support?
Deepgram Aura (Legacy) accepts text and produces audio according to its architecture metadata on LLM.API.
Is Deepgram Aura (Legacy) a chat model?
No—Deepgram Aura (Legacy) is categorized as a tts model. Use the matching API surface rather than assuming chat completions.
Does Deepgram Aura (Legacy) support streaming?
Streaming depends on the active provider; check the providers table on this page for flags.
Which providers serve Deepgram Aura (Legacy)?
LLM.API currently lists: deepgram. Availability can vary by region and account.
How do I call Deepgram Aura (Legacy) via API?
Send OpenAI-compatible requests to https://api.llmapi.ai/v1 with model "aura" and your LLM.API key. See the code snippet on this page.
Can I use tools or structured outputs with Deepgram Aura (Legacy)?
Tooling support varies; for pure tts models, prefer the modalities listed rather than assuming chat tools.
Where is the canonical page for Deepgram Aura (Legacy)?
https://llmapi.ai/models/aura/
When should I choose Deepgram Aura (Legacy)?
You want API-driven voice prototypes that can go to production — especially when you specifically need Deepgram Aura (Legacy).
What is the context length for Deepgram Aura (Legacy)?
Reported context for Deepgram Aura (Legacy) is See provider specs. Always verify the active provider row if multiple providers are listed.
What is Deepgram Aura (Legacy)?
Text-to-speech model by Deepgram. On LLM.API it is addressed as `aura`.
Get one key to every model
Swap your API key. Keep your code.