Deepgram

Deepgram · United States · Speech & audio
Global Closed sourceFree tierIndependent test
Showing version: Nova-3 · 2025-02-01 · Version lineage ↓
Nova-3Nova-2
01

Overview

Deepgram's developer-first speech recognition API platform, led by the Nova ASR line (current Nova-3, plus Flux for conversational streaming), known for low-latency streaming transcription, per-minute pricing and diarization.

Release date2025-02-01
02 / Provenance

Field checks and source notes

When sources disagree on a field, every reading is listed here with its own citation. We do not take a midpoint, invent a missing figure, or decide which side is right — follow the citation and judge for your case.

These field-level notes are recorded verbatim in Chinese in the source data. Open the Chinese version

03 / Plain layer

Plain-language benchmarks

Naturalness Not disclosed
Accuracy (WER) 5.2% · lower is better
Speed / latency Not disclosed
Languages supported Not disclosed
Price / free Not disclosed新账户 $200 额度
04

Practical facts

Context lengthNot disclosed
Max outputNot disclosed
ParametersNot disclosed
InputNot disclosed
Output priceNot disclosed
CNYNot disclosed
Free tierNew accounts receive $200 of credit.
Output speedNot disclosed
Release date
LicenseNot disclosed
Show technical data

Technical benchmark table

BenchmarkScoreMax / unit Source typeSourceTest dateConditions
ASR word error rate
asr-wer
5.2% percent / 100 Independent test AA-WER 指数:约 8 小时、三数据集按时长加权平均,批量转写;越低越好
05

Version lineage

Back to family page →
VersionRelease dateStatus OpennessParametersWhat changed Detail
Nova-3Showing version Active Closed source Not disclosed Released February 2025 for batch and streaming transcription; vendor launch figures cite ~6.84% streaming WER and ~5.3% median batch WER (self-reported), with medical variants and the later Flux conversational model. Detail
Nova-2 Superseded Closed source Not disclosed Previous flagship superseded by Nova-3; exact release date not verified in this pass and left blank. Detail

Last updated: · Sources on detail page

06 / Compare

Comparable in this category

Cartesia Sonic
Doubao Speech
ElevenLabs
iFLYTEK Speech (Spark Speech / XFYun)
0 / 3 Compare Open comparison →