Microsoft Olive

by Microsoft

Model-optimization toolchain — Whisper ONNX/QNN/DirectML targets.

TL;DR

Model-optimization toolchain — Whisper ONNX/QNN/DirectML targets.

Best for optimizing Whisper for Windows on Snapdragon / Intel NPUs. Pricing: free.

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

What it is

Microsoft's open optimization framework for ONNX-based deployment. MIT.

Best for: Optimizing Whisper for Windows on Snapdragon / Intel NPUs.
Watch out for: Recipe-driven; learning curve.

Install / use

pip install olive-ai

Features

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

Microsoft Olive vs Whipscribe

FeatureMicrosoft OliveWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to Microsoft Olive

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.