NVIDIA: Nemotron 3.5 Transcribe 30B

One API key. Live prices. Ready-to-run code.

NVIDIA's open 30B-A4B speech model for offline transcription in 40 languages, for recordings up to an hour.

Served on OneInfer by DeepInfra. Use it with the same API key and pay-as-you-go wallet as every other model in the catalog.

ProviderDeepInfranvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

Call Nemotron 3.5 Transcribe 30B in 4 steps

Step 1 of 4

Create a key in the Console. The same key works for every model on OneInfer.

OverviewProvidersPricingBenchmarksAPI and quickstartReviews
Context
N/A
Input
audio
Output
text
Tool calling
Not listed

About this model

NVIDIA's open 30B-A4B speech model for offline transcription in 40 languages, for recordings up to an hour.

Input modalities

  • audio

    Accepted as model input

Providers

Available routing options for this model through OneInfer.

  • DeepInfra
    Available
    Speech transcription
    $0.132 / hour
    Routing
    OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Speech transcriptionSTT$0.132 / hour

Performance and benchmarks

Independent evaluations and live cluster operational metrics

We haven’t measured this model yet.

API guide

API docs

  1. Generate your access token

    Use your API key to generate the JWT access token required by the Models API.

  2. Add the JWT token

    Copy the generated JWT token and replace JWT_TOKEN in the example below.

  3. Check your credits

    If your balance is too low, before calling the model.

  4. Run the API example

    Choose your preferred language, copy the example, and send your first model request.

    curl -X POST https://api.oneinfer.ai/v1/ula/transcribe \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -F "file=@audio.mp3" \
  -F 'transcription_request_json={"model":"nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B","language":"en","response_format":"verbose_json","timestamp_granularities":["word"]}'

Community reviews and ratings

Visitor and developer evaluations of NVIDIA: Nemotron 3.5 Transcribe 30B's real-world intelligence, code accuracy, and speed

No ratings yet

Top community tags

Be the first to rate and tag this model's coding and reasoning strengths.

No community reviews yet

Be the first to share developer feedback on NVIDIA: Nemotron 3.5 Transcribe 30B's latency, code accuracy, and reliability in production.