ReferenceAsk
Remy Reference/models/Nemotron 3.5 Transcribe
D

Nemotron 3.5 Transcribe

Nemotron 3.5 Transcribe, a transcription model from DeepInfra.
transcriptionModelOverride: { model: "nemotron-3.5-transcribe" }
Nvidia·served viaDeepInfra·Released October 2026
Pricing
Per second
$0.000033
Per minute
$0.0020
Per second
$0
Per minute
$0
Specifications
Released
October 2026
Model string
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
Capabilities
Open sourceMultilingualLow cost
Parameters
Model options, passed in transcriptionModelOverride.config.
ParameterTypeDefaultRange / options
language
The spoken language, as a code such as en or es. Leave as Auto to have the model detect it.
Select—enesfrdeitpt+7
includeWordTimings
Add per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably.
Selectnoyesno
subtitles
Also return the transcript as a subtitle file, SRT or WebVTT, timed to the audio.
Select—srtvtt
Use this model
await mindstudio.transcribeAudio({
  audioUrl: "...",
  transcriptionModelOverride: {
    model: "nemotron-3.5-transcribe",
    config: {
      includeWordTimings: "no",
    },
  },
});