xpu liveBETA
Models›Aura-2

Aura-2

Model reference ↗

Model ranking

Not matched to the current verified ranking snapshot.

Pricing 1 Model information

Provider prices 1

Lowest input price per billing unit. Conditions in Details.

ProviderPriceProvider model IDStatusMedia deployment detailsSource
Cloudflare Workers AIaura-2-en
Standard
Usage $0.03USD / 1,000 characters
Updated 2026-11-22 · 15:43 UTC
@cf/deepgram/aura-2-enCatalog-listed
Conditions

Public catalog listing; account eligibility and capacity can vary. Verified component tariffs are supplied by the existing pricing engine.

Not suppliedOfficial source ↗2026-10-20
Cloudflare Workers AIaura-2-es
Standard
Usage $0.03USD / 1,000 characters
Updated 2026-11-22 · 15:43 UTC
@cf/deepgram/aura-2-esCatalog-listed
Conditions

Public catalog listing; account eligibility and capacity can vary. Verified component tariffs are supplied by the existing pricing engine.

Not suppliedOfficial source ↗2026-10-20

Aura-2 is Deepgram’s second-generation speech synthesis family. Its English and Spanish Cloudflare endpoints are kept as language-specific deployments on one model page.

Aura-2: suitable applications

Use the English or Spanish route to produce spoken replies, narration and voice-agent output with a documented speaker selection.

Capabilities and technical details

The endpoint exposes voice, encoding and container options, making it possible to match speech output to the application’s playback path.

The model accepts text and returns audio. The recorded terms are Deepgram hosted-service terms; the linked source explains their scope.

Limitations and selection

Speaker lists differ between the English and Spanish routes. Character-based billing should not be confused with the minute-based tariff of a transcription model.

Choose the language route first, then compare pronunciation and streaming behavior with representative text. Keep the speaker name and encoding in deployment tests.

Cloudflare API pricing

Aura-2 uses the billing components shown in the provider table. Keep the quoted audio-minute, character or request unit intact when estimating usage; those measurements are not interchangeable.

Review the official Cloudflare endpoint reference and the Deepgram model documentation. Compare the linked Cloudflare Workers AI provider profile with the xpu live model directory when selecting a deployment.

OUTPUTaudioAudio & speech
DEVELOPERDeepgramOriginal model / service creator
PROVIDERS1Linked in this catalog
SOURCE CHECKED2026-10-20Sources reviewed; unknown fields labeled

Media specifications

Audio format / quality
Encoding and sample rate depend on selected speaker/endpoint; see Cloudflare schema.
Languages
English, Spanish (separate Cloudflare endpoints)

These describe the linked model reference. Individual provider endpoints can support different limits and options.

Specifications

Catalog model ID
deepgram/aura-2
Developer model ID / revision
Not verified in cited sources
Weight access
Not verified in cited sources
Weight license / access terms
Deepgram hosted-service termsDeveloper weight license / hosted access terms ↗
Total parameters (billions)
Not verified in cited sources
Download size (GB)
Depends on checkpoint and precision; no verified file size
Release date
Not verified in cited sources
Notes
Cloudflare deployment limits and transport options are recorded on its offering. Weight license is separate from hosted-service conditions.

Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Arena user-preference scores are checked automatically every six hours against the latest published Text / overall dataset. Source: Arena / LMArena; CC BY 4.0. Selection and catalog matching by XPU LIVE. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.