Transcription model
Nova 3
deepgram/nova-3
deepgram/nova-3 is a speech-to-text model from Deepgram you can call on the OceanToken API at $0.0043 per minute of audio.
At a glance
| Model ID | deepgram/nova-3 |
|---|---|
| Type | Transcription |
| Publisher | Deepgram |
| Price | $0.0043 per minute of audio |
| Endpoint | /v1/audio/transcriptions |
| API shape | OpenAI-compatible |
| In the catalog since | 2026-07-15 |
Call it
Base URL https://api.oceantoken.ai/v1, your OceanToken key as the bearer token, and the model ID above as model. The OpenAI SDKs work unchanged; see your first request.
curl https://api.oceantoken.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $OCEANTOKEN_API_KEY" \
-F model="deepgram/nova-3" -F file=@meeting.mp3
Compared with similar models
Transcription models on OceanToken closest to deepgram/nova-3 in price. Every price is what you pay, in US dollars, with no platform fee on top.
| Model | Publisher | Context | Price (per minute) |
|---|---|---|---|
| Nova 3 | Deepgram | $0.0043 | |
GPT Transcribeopenai/gpt-transcribe | OpenAI | $0.0045 | |
Transcribe 1fish-audio/transcribe-1 | Fish Audio | $0.006 | |
Whisper 1openai/whisper-1 | OpenAI | $0.006 |
More from Deepgram
- Aura 2
deepgram/aura-2
All Deepgram models on OceanToken
Use it
Create an account All models and prices
Prices and capabilities on this page were read from the live OceanToken catalog on 2026-10-18 (UTC), when the documentation was built. If a price has changed since, the console's Models page shows the current one.