AudioLLMs/AudioBench

AudioBench: A Universal Benchmark for Audio Large Language Models

39
/ 100
Emerging

When evaluating or building audio AI models, comparing their performance across various tasks and languages can be complex. This tool helps you benchmark how well different "Audio Large Language Models" perform. You input an audio AI model, and it outputs a performance score across over 50 datasets for tasks like speech recognition, translation, and question answering, letting you compare models directly. This is for researchers and developers working with cutting-edge audio AI.

297 stars. No commits in the last 6 months.

Use this if you need a comprehensive, standardized way to measure and compare the capabilities of different audio AI models across many real-world audio tasks and languages.

Not ideal if you're looking for an off-the-shelf audio AI model to directly integrate into an application, as this tool is for evaluation, not deployment.

audio-AI-evaluation speech-recognition-benchmarking natural-language-processing multimodal-AI AI-model-comparison
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

297

Forks

15

Language

Python

License

Last pushed

Jun 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/AudioLLMs/AudioBench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.