NTU Speech Processing Lab

by National Taiwan University

National Taiwan University Speech Lab — S3PRL + SUPERB origins.

Looking at NTU Speech Processing Lab? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

Best for self-supervised speech representations; SUPERB benchmark family. Pricing: free.

Category
Open source
License
Apache-2.0
Stars
★ 2.6k
Last push
2026-03-12
Pricing
free
Platforms
Web

What it is

NTU Speech Lab (Hung-yi Lee group) shipped S3PRL + SUPERB + ML-SUPERB — the canonical SSL probing benchmark and toolkit. Driving force behind multilingual self-supervised speech evaluation.

Best for: Self-supervised speech representations; SUPERB benchmark family.
Watch out for: Academic; toolkits Apache-2.0.

Install / use

Go to NTU Speech Processing Lab speech.ee.ntu.edu.tw

Features

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

Links

GitHub repo ↗

NTU Speech Processing Lab vs Whipscribe

FeatureNTU Speech Processing LabWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarizationNoYes
Word timestampsNoYes
StreamingNoNo
Languages099
PlatformsWebWeb, API, MCP

Alternatives to NTU Speech Processing Lab

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 107.0k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 24.8k

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.