CUTLASS

by NVIDIA

High-performance CUDA matrix kernels used by Whisper engines.

TL;DR

High-performance CUDA matrix kernels used by Whisper engines.

Best for custom Whisper / Conformer kernels with sparsity or FP8. Pricing: free.

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

What it is

NVIDIA's open template library for high-performance GEMM. BSD-3-Clause.

Best for: Custom Whisper / Conformer kernels with sparsity or FP8.
Watch out for: C++/CUDA expertise required.

Install / use

git clone https://github.com/NVIDIA/cutlass

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported99
HIPAA eligibleNo

CUTLASS vs Whipscribe

FeatureCUTLASSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinuxWeb, API, MCP

Alternatives to CUTLASS

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.