Microsoft Recognizers-Text

by Microsoft

Post-processing for ASR: numbers, dates, units in 20+ languages.

TL;DR

Post-processing for ASR: numbers, dates, units in 20+ languages.

Best for normalizing transcripts: monetary amounts, dates, durations. Pricing: free.

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

What it is

A multi-language entity-recognition library tuned for spoken/written normalization. MIT.

Best for: Normalizing transcripts: monetary amounts, dates, durations.
Watch out for: Rule-based; not for free-text correction.

Install / use

pip install recognizers-text-suite

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported20
HIPAA eligibleNo

Microsoft Recognizers-Text vs Whipscribe

FeatureMicrosoft Recognizers-TextWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages2099
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to Microsoft Recognizers-Text

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.