Scribe v2 vs Nova-3
ElevenLabs's Scribe v2 and Deepgram's Nova-3 both target speech generation, but they price and behave differently. Here is the side-by-side.
Pricing checked against provider documentation on . How we verify
The short answer
Scribe v2 is the cheaper option — roughly 1.2x less on a blended workload, and it suits widest language coverage with diarization. Nova-3 justifies its premium when you need real-time streaming transcription.
ElevenLabs • Scribe
$0.00 / $
/ audio min (input / output)
Transcription across 99 languages with speaker diarization and word-level timestamps, billed at $0.22 per audio hour. Worth knowing that ElevenLabs credits are shared across its products, so heavy text-to-speech use can eat into the same allowance your transcription draws from.
Deepgram • Nova
$0.00 / $
/ audio min (input / output)
Built for streaming rather than batch, with the low latency and concurrency handling that live captioning and voice agents need. Deepgram also sells a managed Voice Agent API on top, which bundles the LLM and TTS legs and prices per conversation minute rather than per transcription minute.
Input price
Nova-3 is 16% more expensive than Scribe v2 on input tokens.
Specification comparison
| Attribute | Scribe v2 | Nova-3 |
|---|---|---|
| Input (/ audio min) | $0.00 | $0.00 |
| Output (/ audio min) | — | — |
| Cached input | — | — |
| Context window | — | — |
| Max output | — | — |
| Native reasoning | No | No |
| Knowledge cutoff | — | — |
| Relative latency | medium | low |
| Open weights | No | No |
| API model ID | scribe-v2 | nova-3 |
| Status | stable | stable |
Scribe v2: Published as $0.22 per audio hour. Entity detection adds $0.07/hour and keyterm prompting $0.05/hour. A realtime variant runs $0.39/hour (~$0.0065/min) at roughly 150 ms latency.
Nova-3: Batch pay-as-you-go rate for the monolingual model. Streaming is higher and quoted between $0.0048 and $0.0077/min depending on plan and source; multilingual adds roughly 20%. Confirm your tier in the console.
Choose Scribe v2 if…
- Multilingual transcription with speakers
- Subtitling with word timings
- Interview and research archives
- Pipelines already using ElevenLabs voices
Choose Nova-3 if…
- Live captioning
- Voice agents and IVR
- Real-time meeting transcription
- Call-centre analytics
Frequently asked
Is Scribe v2 or Nova-3 cheaper?
Scribe v2 is cheaper. On a blended 3:1 input-to-output workload it costs about 1.2x less than Nova-3.
Which has the larger context window, Scribe v2 or Nova-3?
Both accept up to — tokens, so context is not a differentiator here.
Should I use Scribe v2 or Nova-3?
Pick Scribe v2 for widest language coverage with diarization. Pick Nova-3 for real-time streaming transcription. If cost dominates the decision, Scribe v2 wins; if you need the capability ceiling, benchmark both on your own evals before committing.