Speech to Text Model
Nemotron 3.5 Transcribe
Transcription by Nvidia
Publisher
Nvidia
NvidiaTypeTranscription
ReleasedOctober 2026
Input$33.33/MTok
OutputFree/MTok
Provider
DeepInfra
DeepInfraReady to build with Nemotron 3.5 Transcribe?
Get Started FreeConfiguration
Parameters & options
LanguageSelect
The spoken language, as a code such as en or es. Leave as Auto to have the model detect it.
Include Word TimingsSelect
Add per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably.
SubtitlesSelect
Also return the transcript as a subtitle file, SRT or WebVTT, timed to the audio.
Mistral
Google
QwenStart building with Nemotron 3.5 Transcribe
No API keys required. Create AI-powered workflows with Nemotron 3.5 Transcribe in minutes — free.