alessandroragano/scoreq
SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)
This tool helps evaluate the quality of spoken audio, whether it's from natural recordings like phone calls or podcasts, or generated by AI like text-to-speech systems. You input an audio file (and optionally a reference clean audio), and it outputs a Mean Opinion Score (MOS) or a quality distance score. This is for anyone who needs to objectively measure and improve speech quality, such as audio engineers, speech synthesis developers, or telecommunications professionals.
108 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need an objective way to measure the perceived quality of natural or synthetic speech, especially for assessing codecs, VoIP systems, or text-to-speech models.
Not ideal if you're evaluating very long audio segments (over 15 seconds) without trimming, or if your audio quality assessment requires a sampling rate significantly higher than 16 kHz without further validation.
Stars
108
Forks
8
Language
Python
License
—
Category
Last pushed
Aug 01, 2025
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/alessandroragano/scoreq"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment