NVIDIA NeMo

by NVIDIA

Toolkit + model zoo behind Canary, Parakeet, Conformer, FastConformer.

TL;DR

Toolkit + model zoo behind Canary, Parakeet, Conformer, FastConformer.

Best for anyone training, fine-tuning, or serving state-of-the-art ASR on NVIDIA GPUs. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux, Docker

What it is

NeMo is NVIDIA's conversational-AI toolkit. Ships Canary-1B/-180M-flash, Parakeet-RNNT/CTC/TDT, Conformer-CTC large, FastConformer, and Citrinet under permissive licenses on NGC. Apache-2.0.

Best for: Anyone training, fine-tuning, or serving state-of-the-art ASR on NVIDIA GPUs.
Watch out for: Heavy install; tight NVIDIA dependency; CPU inference impractical.

Install / use

pip install nemo_toolkit[asr]

Features

Speaker diarizationYes
Word-level timestampsYes
Streaming / real-timeNo
Languages supported60
HIPAA eligibleNo

NVIDIA NeMo vs Whipscribe

FeatureNVIDIA NeMoWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationYesYes
Word timestampsYesYes
StreamingNoNo
Languages6099
PlatformsLinux, DockerWeb, API, MCP

Alternatives to NVIDIA NeMo

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.