MERL Speech

by Mitsubishi Electric Research Labs

Mitsubishi Electric Research Labs Speech Group — CHiME + speech-enhancement leaders.

TL;DR

Mitsubishi Electric Research Labs Speech Group — CHiME + speech-enhancement leaders.

Best for speech separation, enhancement, far-field meeting ASR research. Pricing: free.

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

What it is

MERL Speech (Hershey + Watanabe lineage) led CHiME challenge organizing, pioneered deep-clustering speech separation, and contributes to ESPnet.

Best for: Speech separation, enhancement, far-field meeting ASR research.
Watch out for: Industrial-lab research output; per-release licenses vary.

Install / use

https://www.merl.com/research/?research=speech-and-audio

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported0
HIPAA eligibleNo

MERL Speech vs Whipscribe

FeatureMERL SpeechWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsNoYes
StreamingNoNo
Languages099
PlatformsWebWeb, API, MCP

Alternatives to MERL Speech

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.