AutoArk/GPA

[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny 300M model!

48
/ 100
Emerging

This project offers a single tool to handle several audio tasks, making it easier to work with spoken content. You can feed it audio to get text back (like transcribing a meeting), give it text to generate spoken audio, or even change the voice in an existing audio clip. It's designed for anyone who needs to manage or create audio, like content creators, educators, or researchers working with speech data.

Use this if you need to perform speech recognition, text-to-speech, or voice conversion and prefer a unified, efficient solution.

Not ideal if you require highly specialized, domain-specific audio processing tools or need to deploy on platforms like iOS or Android, which are not yet fully supported.

audio-transcription voice-generation speech-editing content-creation language-learning
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 13 / 25
Community 16 / 25

How are scores calculated?

Stars

97

Forks

16

Language

Python

License

Apache-2.0

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

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

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