F
FluidAudio
FluidInference/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.
★2.6kstars
Swift
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Models project leveraging ane and asr, built with Swift, open-source
Who made it?Maintained by FluidInference team, 2.6K⭐ on GitHub, #561 out of 3201 in Models
Why does it exist?The FluidInference team recognized that existing ane tools in Models were hard to use. FluidAudio was designed to make asr more accessible.
What can it do?Key use cases: audio, automatic-speech-recognition, avfoundation
How to install with AI?Use an AI coding assistant to follow the README and automatically handle the install and environment setup.
🔗 github.com/FluidInference/FluidAudio | 官网 https://docs.fluidinference.com/introduction
🔗 github.com/FluidInference/FluidAudio | 官网 https://docs.fluidinference.com/introduction
Topics
aneasraudioautomatic-speech-recognitionavfoundationcoremliosmacosnvidiaparakeetreal-timespeaker-diarizationspeaker-embeddingspeaker-identificationspeaker-recognitionspeech-to-textswiftvadvoice-activity-detection