None
None
Long Story Video Skill
Turn your idea into 10s–10min video—AI writes scripts, prompts, and generates footage automatically.
Ads Video Skill
Generate professional ads and sales videos—AI auto-generates scripts, prompts, and footage.
3D Science Explainer Video Skill
Convert scientific concepts into stunning 3D explain animations
Feedback
freeTrialImage.bannerPity
freeTrialImage.upgradeUnlock
- ✓freeTrialImage.benefitHd
- ✓freeTrialImage.benefitWatermark
- ✓freeTrialImage.benefitUnlimited
nemotron transcribe
Type what you want the transcript to look like and Nemotron transcribe follows it — hour-long audio, 40 languages, speaker labels, word-level timings.
All Tools
Discover our comprehensive AI-powered animation toolkit
MiniMax H3
MiniMax H3 AI Video Generator
Seedance 2.5
The Future of AI Video Is Here.
Seedance 2.0
The Future of AI Video Is Here.
Seedance 2.0
The Future of AI Video Is Here.
Gemini Omni
Gemini Omni Video Generator
Image to Video
Generate videos from images
Gemini Omni 1.2 Flash
AI Multi-Scene Shorts Generator
Create viral AI Shorts instantly
One Model, Many Transcription Conventions
Transcript conventions differ from team to team. Nemotron Transcribe lets you name the format you want in plain words and holds to it for the whole recording.
- Styles Set by Plain-Language PromptsVerbatim, written-form, contextual and speaker-attributed output, each one requested in the prompt rather than fixed at training time.
- Speech Encoder Paired with a Hybrid MoE LLMA speech encoder, a frozen diarization model and a 30B-A3B hybrid MoE language model with roughly 4.3B active parameters.
- Open Weights Plus a Fine-Tuning ToolkitOpenMDW-1.1 checkpoints arrive in BF16, FP8, NVFP4, GGUF and DFlash2 formats, alongside the NeMo Speech toolkit for Nemotron Transcribe.
Running Nemotron Transcribe in Three Moves
Load a checkpoint, phrase the instruction, then decode and align — and an attributed transcript comes back.
What Nemotron Transcribe Brings to Your Audio
Top Open ASR Leaderboard scores, per-speaker attribution on overlapping talk and fast NIM inference — the strengths behind Nemotron Transcribe.
Leaderboard-Topping Accuracy
A mean WER of 4.71% across the 9 English Open ASR test sets, and 4.62% on the multilingual board.
Who Spoke, Even When Voices Overlap
From one-minute clips to full meetings, it is the first SALM to outperform cascaded systems on attributed ASR.
Entity Lists Cut Name Errors
Supplying expected entities reduces named-entity errors six-fold on ContextASR-Bench, thanks to the parallel expert encoder.
Timestamps Tied to Each Speaker
A small CTC adapter maps the finished transcript back onto the audio, so long overlapping calls still get per-speaker timings.
Faster Decoding, Higher Throughput
The model's MTP layer or a DFlash2 draft accelerates decoding; the NVFP4 NIM processes 2,238 audio seconds per second on one RTX PRO 6000 Blackwell.
Adapt on a Single GPU
A supervision-balanced mixture lets one GPU pick up new languages and domains in about 0.5–2.3 GPU-hours per task.
Nemotron Transcribe: Your Questions Answered
Straight answers on Nemotron Transcribe — benchmark scores, language coverage, timestamps, licensing and available checkpoints.
What exactly is Nemotron Transcribe?
A speech-augmented language model that pairs a speech encoder and a frozen diarization model with a 30B-A3B hybrid MoE LLM.
Which output styles can I ask for?
Verbatim, written-form, contextual, speaker-attributed and rich transcription, plus translation and language ID — each one selected by an instruction.
How does it score on public benchmarks?
A 4.71% mean WER across the 9 English leaderboard sets, 4.62% multilingual, and six times fewer named-entity errors on ContextASR-Bench.
How much audio can one job handle, and in how many languages?
A single Nemotron Transcribe checkpoint covers recordings up to an hour in 40 languages, code-switched speech included.
Does it identify who spoke, and at what moment?
Yes — overlapping multi-speaker audio is attributed per speaker, and per-speaker word timestamps come back on request.
What checkpoints and license ship with it, and can I fine-tune?
OpenMDW-1.1 weights arrive as BF16, FP8, NVFP4, GGUF and DFlash2 files; NeMo Speech fine-tunes them in roughly 0.5–2.3 GPU-hours per task.
Put Nemotron Transcribe to Work on Your Audio
Choose a checkpoint, serve it through the NIM, then send your first instruction-led request: styled output, translation, language ID and speaker timings across 40 languages.