inclusionAI/Ming-UniAudio

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

44
/ 100
Emerging

This project helps audio content creators and developers work with spoken audio. It takes speech input and can generate new speech, understand spoken content, or edit existing audio based on text instructions. Anyone who needs to produce, analyze, or modify speech, like podcasters, voiceover artists, or researchers, would find this useful.

435 stars.

Use this if you need to perform multiple tasks like transcribing, generating, or editing speech using simple text commands, especially for complex changes without needing to specify exact timestamps.

Not ideal if you only need a basic speech-to-text or text-to-speech tool and don't require advanced editing or combined capabilities.

audio-editing speech-synthesis speech-recognition voice-production podcast-creation
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

435

Forks

28

Language

Python

License

MIT

Last pushed

Nov 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/inclusionAI/Ming-UniAudio"

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