Deepgram Nova-3

deepgram/nova-3 · by Deepgram · end-to-end-asr

Pricing — 1 offering(s)

Deepgram

About this offering: Deepgram's Nova-3 speech-to-text, billed per second of audio. Pay-as-you-go pre-recorded audio costs $0.0043 per minute ($0.0052 multilingual). Streaming costs $0.0077 per minute ($0.0092 multilingual) at the regular rate. A promotional streaming rate of $0.0048 per minute ($0.0058 multilingual) runs through February 13, 2027, per the pricing page's structured data; the regular rate returns on February 14 (https://deepgram.com/pricing, checked 2026-11-14). The Growth plan ($4,000+ a year) lowers rates to $0.0036 per minute pre-recorded and $0.0065 streaming (checked 2026-10-30).

Pre-recorded audio (batch)

$0.0043 / minute Current 2025-01-01 → present
Pay-as-you-go rate for monolingual pre-recorded audio. Multilingual transcription costs $0.0052/min.

Streaming (real-time)

$0.0077 / minute Historical 2025-01-01 → 2026-11-12

Pay-as-you-go regular streaming rate. Deepgram also shows a promotional $0.0048/min (monolingual) under…

Pay-as-you-go regular streaming rate. Deepgram also shows a promotional $0.0048/min (monolingual) under "Limited-time promotional rates on streaming", with no end date (checked 2026-10-27); an undated promotion isn't recorded as the price.
$0.0048 / minute Current 2026-11-13 → 2027-02-13

Promotional streaming rate: $0.0048 per minute (monolingual), down from the regular $0.0077, valid through…

Promotional streaming rate: $0.0048 per minute (monolingual), down from the regular $0.0077, valid through February 13, 2027. The end date is from the pricing page's structured data (schema.org priceValidUntil); the visible page says only "Promo pricing" and "$0.0048 was $0.0077 / min". The start date is the earliest day the promotion was seen with an end date, not a date Deepgram stated. Multilingual streaming is $0.0058 during the promotion (regular $0.0092).
$0.0077 / minute Future 2027-02-14

Regular streaming rate, $0.0077 per minute (monolingual), from February 14, 2027, when the promotional rate…

Regular streaming rate, $0.0077 per minute (monolingual), from February 14, 2027, when the promotional rate ends. Deepgram's table shows it as the "was" price during the promotion.

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

See how Deepgram Nova-3 fits into a cost-aware routing setup

About Deepgram Nova-3

Deepgram Nova-3 is a proprietary end-to-end ASR model trained on diverse audio — phone calls, meetings, broadcast media — rather than primarily on clean read speech. Over its predecessor Nova-2 it adds better punctuation, entity recognition and accent robustness. It is English-first; multilingual coverage is growing but its quality lags English noticeably.

Two things set it apart on the product side. Speaker diarization is built in via a `diarize=true` parameter and included in the base price, with no add-on surcharge unlike some competitors. And billing is per second with no minimum duration, which keeps cost predictable — though the streaming tier runs roughly 80% more expensive per minute than batch, and there is no native translation endpoint.

Deepgram positions Nova-3 as state-of-the-art on its own proprietary benchmarks (earnings calls, phone audio) and does not publish a LibriSpeech WER, so there is no standard independent accuracy number for it. The best-in-class streaming latency it cites — about 300ms round trip on Deepgram-hosted infrastructure — is vendor-reported and not independently verified.

Capability profile

How Deepgram Nova-3 rates across core capability dimensions, with the task-level evidence behind each rating.

transcription accuracy Strong

State-of-the-art WER across accents and audio conditions. Particularly strong on phone-quality and noisy recordings. Improves on Nova-2 with better punctuation and entity recognition.

language support Moderate

English-first with growing multilingual support. Coverage and accuracy are weaker than English; check Deepgram docs for the current language list.

speaker diarisation Strong

Built-in diarization via diarize=true parameter. Accurate multi-speaker segmentation on meetings and conference audio. Included in base price — no add-on surcharge unlike some competitors.

real time streaming Strong

Best-in-class streaming at ~300ms latency on Deepgram infrastructure. Per-second billing with no minimum duration. Supports interim results with is_final flags for display-while-speaking UX.

custom vocabulary Strong

Keywords API supports custom word lists and phrase boosting for domain- specific terminology, product names, and proper nouns.

Benchmarks

Benchmark	Score	Config	Source
Real-time streaming latency (vendor-reported)	300 ms	Round-trip latency on Deepgram-hosted infrastructure. Vendor-reported, not independently verified.	source ↗
WER (LibriSpeech)	—	Deepgram does not publish LibriSpeech WER. Nova-3 is positioned as state-of-the-art on proprietary benchmarks including earnings calls and phone audio.	—

Operator guidance

The default choice for high-accuracy production STT. Best-in-class streaming latency makes it ideal for real-time apps; per-second billing (no rounding) keeps cost predictable. Use Whisper-1 for broad 99-language coverage or if you are already on the OpenAI platform. Use Universal-2 for the lowest per- minute rate on batch workloads.