Deepgram Nova-2
converts spoken audio into text. Sometimes called "ASR" (automatic speech recognition). Deepgram, AssemblyAI.fact-checked, all required fields present, publicly visiblereal-time
speech.dev has not published an operational assessment for this entry yet. Facts below are source-linked where available.
Overview
- Publisher
- Deepgram
- Lab
- deepgram
- Last updated
- 2026-05-23
- Modality
- converts spoken audio into text. Sometimes called "ASR" (automatic speech recognition). Deepgram, AssemblyAI.
a voice model trained on multiple languages. Quality varies enormously by language — "supports 40 languages" may be great in 3 and mediocre in the other 37.
en-us, en-gb, es, fr, de, pt, nl, hi, ja, ko, zh
Pricing
- Billing model
- Per minute
- Rate
- $0.0043 per minute
Last verified May 23, 2026
Technical
- Streaming
- Supported · bidirectional
- Hosting
- saas-vendor-cloud
- Self-hostable
- No
API access
WSS
API endpoints
wsshttps
SDK languages
python, typescript, go, csharp
Regions (vendor buckets)
Macro areas as published by the vendor (often broad; not a country list).
Compliance (vendor-published)
CCPAGDPR DPAHIPAA BAAPCI DSSSOC 2 Type ISOC 2 Type II
LiveKit Inference
Listed on LiveKit Agents inference catalog · verified 2026-05-23
| Listed model | Build & Ship | Scale |
|---|---|---|
| Nova-2 | $0.0058 | $0.0047 |
| Nova-2 Conversational AI | $0.0058 | $0.0047 |
| Nova-2 Medical | $0.0058 | $0.0047 |
| Nova-2 Phone Call | $0.0058 | $0.0047 |
LiveKit inference pricing (per minute)
Suggest an update
Facts-layer corrections only — source URLs required. Opens a GitHub issue; a maintainer runs the content agent after triage. Not for operational notes.
Lab metadata: Update Deepgram · All request types · Full guide