FluidAudio

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

Forked from FluidAudio by Fluid Inference.
Written by Brandon Weng and 52 other contributors.
In development for over 1 year, with 454 commits and 43 releases.
There are no open issues and 4 open pull requests. The last pull request was merged/closed 10 days ago.
This package depends on 11 other packages.
Including all transitive and test dependencies.
Apache 2.0 licensed
5 stars
1 library
1 executable
No plugins
No macros
Zero data race safety errorsWhat is data race safety and how is it tested?

Compatibility

Full Build Results

v0.13.2
6.4
6.3
6.2
6.1
main
6.4
6.3
6.2
6.1

v0.13.2/main
iOS
macOS
visionOS
watchOS
tvOS
Linux
Wasm
Android

Package ID	473C2605-D1F1-467C-A7FA-88373AEBC8BB
Score	95

Swift Package Index

When working with an Xcode project:

When working with a Swift Package Manager manifest:

Compatibility