Skip to main content
MindStudio
Pricing
BlogAbout
My Workspace
Speech to Text Model

Deepgram Nova-3

Transcription by Deepgram

PublisherDeepgram
TypeTranscription
ReleasedFebruary 2025
Price$0.0043 / min of audio
REALTIMELOW LATENCYACCURATE

Ready to build with Deepgram Nova-3?

Get Started

Parameters & options

Include SpeakersSelect

Label each utterance with a speaker index when multiple people talk.

Default: no
YesNo
LanguageSelect

The spoken language, as a code such as en or es.

Default: en
Multilingual (switches language)EnglishSpanishFrenchGermanItalianPortugueseDutchHindiJapaneseKoreanChineseArabicRussian
Detect LanguageSelect

Detect the spoken language instead of assuming English. Leave off for known-English audio.

Default: no
YesNo
Key TermsText Array

Names, products and terms the audio contains, so the model spells them right.

Redact Personal InformationSelect

Replace names, phone numbers, addresses and other personal information in the transcript with a label of what was there.

Default: no
YesNo
Include Word TimingsSelect

Add per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably.

Default: no
YesNo
SubtitlesSelect

Also return the transcript as a subtitle file, SRT or WebVTT, timed to the audio.

NoneSRTWebVTT

Start building with Deepgram Nova-3

No API keys required. Create AI-powered workflows with Deepgram Nova-3 in minutes.