Const-me Whisper

by Const-me

Whisper running on Windows via DirectCompute / GPGPU.

TL;DR

Whisper running on Windows via DirectCompute / GPGPU.

Best for windows desktops with consumer NVIDIA / AMD / Intel GPUs (no CUDA install). Pricing: free.

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

What it is

A C++ port of Whisper that runs the encoder + decoder on Direct3D 11 compute shaders. Works on any DX11 GPU on Windows, including iGPUs. MPL-2.0 / MIT-licensed.

Best for: Windows desktops with consumer NVIDIA / AMD / Intel GPUs (no CUDA install).
Watch out for: Windows-only; uses HLSL compute shaders; no Linux/macOS port.

Install / use

git clone https://github.com/Const-me/Whisper

Features

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

Const-me Whisper vs Whipscribe

FeatureConst-me WhisperWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsWindowsWeb, API, MCP

Alternatives to Const-me Whisper

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.