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

Deepgram Nova 3

Up to 30%

Deepgram Nova 3 brings speech-to-text speech-to-text to LLM.API for voice notes, calls, and caption pipelines.

Start Using API

What is Deepgram Nova 3?

Deepgram Nova 3 is a speech-to-text model on LLM.API (`nova-3`). Speech-to-text model by Deepgram. Feed audio and receive text transcripts for captions, agents, and searchable archives.

Providers

LLM.API routes Deepgram Nova 3 to the providers below, with discounted effective rates versus list price.

ProviderPricingContextCapabilities
deepgram30% offin $0.0043; out — per minute of audio——

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

Try this model

Test Deepgram Nova 3 right here — free to start.

Deepgram Nova 3
Hi! Want to test the model?

Suggestions for your first prompt

Code snippet

Call Deepgram Nova 3 through the OpenAI-compatible API — STT 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="nova-3",
    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": "nova-3",
  "messages": [
    {"role": "system", "content": "You are a precise product assistant."},
    {"role": "user", "content": "Give me three crisp launch checklist items."}
  ]
}

5 Core Capabilities

  • Multilingual audio

    Handles diverse accents and languages depending on the model. Tuned to how teams typically call Deepgram Nova 3.

  • Voice UX input

    Powers voice-driven product interfaces and IVR handoffs. Reflects speech-to-text positioning for this endpoint.

  • Streaming recognition

    Supports low-latency partial transcripts when the provider offers streaming STT.

  • Speech transcription

    Converts spoken audio into text for captions, notes, and search. Tuned to how teams typically call Deepgram Nova 3.

  • Downstream LLM prep

    Feeds transcripts into summarization and action-item extractors. Tuned to how teams typically call Deepgram Nova 3.

6 Most Valuable Use Cases

  • Clinical or field note dictation workflows with Deepgram Nova 3
  • Podcast and video caption drafts
  • Call-center transcription and QA with Deepgram Nova 3
  • Compliance recording text archives
  • Live captioning prototypes with Deepgram Nova 3
  • Meeting notes and searchable recordings

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 Nova 3 on LLM.API?

  • Unified AI Routing

    Production: Reach Deepgram Nova 3 and sibling models through one OpenAI-compatible endpoint.

  • Cost Control

    Compare provider price points and keep spend visible as you scale Deepgram Nova 3.

  • Reliability Layer

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

  • Observability

    Trace prompts, tokens, and errors for Deepgram Nova 3 alongside the rest of your stack.

  • Drop-in SDKs

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

  • Model Breadth

    Swap Deepgram Nova 3 for chat, media, or embedding alternatives without rewriting auth.

When to Use — When NOT to Use

Use it if...

  • You need speech-to-text for batch or streaming audio (Deepgram Nova 3)
  • You will pipe transcripts into search or LLM summarization (Deepgram Nova 3)
  • Voice is a primary input modality in your product (Deepgram Nova 3)

Avoid if...

  • You need text-to-speech or chat generation instead of transcription
  • Your audio cannot leave your compliance boundary and you lack an approved provider path
  • You require guaranteed perfect transcripts for every accent without evaluation

COMMUNITY

What developers say about speech-to-text 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 Nova 3.

  • Head-to-head tests of the leading APIs land within a point or two of each other; the choice usually comes down to language coverage, streaming latency and batch pricing.
  • Voice-agent developers report streaming latency and endpointing quality matter more in production than headline word-error rates.
  • Whisper-family models remain the default open baseline, with hosted providers winning on real-time features and diarization.

SOURCES

Frequently Asked Questions

  • What is the context length for Deepgram Nova 3?

    Reported context for Deepgram Nova 3 is See provider specs. Always verify the active provider row if multiple providers are listed.

  • Is Deepgram Nova 3 a chat model?

    No—Deepgram Nova 3 is categorized as a stt model. Use the matching API surface rather than assuming chat completions.

  • How is Deepgram Nova 3 priced on LLM.API?

    Listed pricing metadata shows: In $4.3 / 1M tokens. LLM.API may offer discounted effective rates (illustrative ~30% callout vs list when available).. Confirm live rates in the LLM.API dashboard or docs before production budgeting.

  • Where is the canonical page for Deepgram Nova 3?

    https://llmapi.ai/models/amazon-nova-3/

  • Does Deepgram Nova 3 translate speech?

    Primary behavior is transcription to text. Translation—if needed—should be a separate step with a chat model unless the provider explicitly offers it.

  • How do I call Deepgram Nova 3 via API?

    Send OpenAI-compatible requests to https://api.llmapi.ai/v1 with model "nova-3" and your LLM.API key. See the code snippet on this page.

  • Can I use tools or structured outputs with Deepgram Nova 3?

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

  • What modalities does Deepgram Nova 3 support?

    Deepgram Nova 3 accepts audio and produces text according to its architecture metadata on LLM.API.

COMPARE

Competitive Models

Get one key to every model

Swap your API key. Keep your code.

Start for free Talk to sales