Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Deepgram / Nova-3

Nova-3 General

Nova-3 speech-to-text model option for general audio.

Transcription
availableClosed weightsSpeech-to-textTranscription
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
6 of 18 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee ratesDeepgram API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
AudioSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Multilingual (English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch): multi , Afrikaans: af, af-ZA, Arabic: ar, ar-AE, ar-SA, ar-QA, ar-KW, ar-SY, ar-LB, ar-PS, ar-JO, ar-EG, ar-SD, ar-TD, ar-MA, ar-DZ, ar-TN, ar-IQ, ar-IR, Armenian: hy, Assamese: as, as-IN, Belarusian: be, Bengali: bn, Bosnian: bs, Bulgarian: bg, Catalan: ca, Chinese (Cantonese, Traditional): zh-HK, Chinese (Mandarin, Simplified): zh, zh-CN, zh-Hans, Chinese (Mandarin, Traditional): zh-TW, zh-Hant, Croatian: hr, Czech: cs, cs-CZ, Danish: da, da-DK, Dutch: nl, English: en, en-US, en-AU, en-GB, en-IN, en-NZ, Estonian: et, Finnish: fi, Flemish: nl-BE, French: fr, fr-CA, Georgian: ka, ka-GE, German: de, German (Switzerland): de-CH, Greek: el, Gujarati: gu, gu-IN, Hebrew: he, Hindi: hi, Hungarian: hu, Indonesian: id, Italian: it, Japanese: ja, Kannada: kn, Kazakh: kk, kk-KZ, Korean: ko, ko-KR, Latvian: lv, Lithuanian: lt, Macedonian: mk, Malay: ms, Marathi: mr, Mongolian: mn, Nepali: ne, Norwegian: no, Pashto: ps, ps-AF, Persian: fa, Polish: pl, Portuguese: pt, pt-BR, pt-PT, Punjabi: pa, pa-IN, Romanian: ro, Russian: ru, Serbian: sr, Slovak: sk, Slovenian: sl, Spanish: es, es-419, Swedish: sv, sv-SE, Tagalog: tl, Tamil: ta, Telugu: te, Thai: th, th-TH, Turkish: tr, tr-TR, Ukrainian: uk, Urdu: ur, Vietnamese: viSource for Languages (opens in a new tab)
Context caching
Not collected

See endpoint caching records. No verified support claim for this model.

API aliases
nova-3, nova-3-generalSource for API aliases (opens in a new tab)
Supported API routes
POST /v1/listen, WebSocket /v1/listenSource for Supported API routes (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Deepgram API

Provider source (opens in a new tab)
API model ID
nova-3
Access
Pre-recorded and streaming transcription through /v1/listen. Specify the language separately.
Regions
Regional routing and residency terms have not been verified for this endpoint.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Monolingual · Pay As You GoStreaming transcription1$0.0048audio minute
Monolingual · Pay As You GoPre-recorded transcription2$0.0043audio minute
Monolingual · GrowthStreaming transcription1$0.0042audio minute
Monolingual · GrowthPre-recorded transcription2$0.0036audio minute
Multilingual · Pay As You GoStreaming transcription3$0.0058audio minute
Multilingual · Pay As You GoPre-recorded transcription2$0.0052audio minute
Multilingual · GrowthStreaming transcription3$0.005audio minute
Multilingual · GrowthPre-recorded transcription2$0.0043audio minute

Rate conditions

  1. Language mode changes the rate. Streaming rate is promotional with no verified expiration date. Regular PAYG rate $0.0077/minute. Growth requires $4,000+/year prepaid; plans are alternatives.
  2. Pre-recorded transcription price. Growth requires $4,000+/year prepaid; plans are alternatives. Optional features may add charges.
  3. Language mode changes the rate. Streaming rate is promotional with no verified expiration date. Regular PAYG rate $0.0092/minute. Growth requires $4,000+/year prepaid; plans are alternatives.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Deepgram API

nova-3
Not verified

Provider-side caching has not been verified for this endpoint. Missing documentation is not evidence that caching is unsupported.

How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Deepgram describes its speech model weights as proprietary, including private deployment under provider control. These named native speech models are catalogued separately from its hosted open-weight Whisper service.

Classification evidence (opens in a new tab)

Sources reviewed