CITATION.cff

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
type: software
title: "FluidAudio: Local Speaker Diarization, ASR, and VAD for Apple Platforms"
abstract: "FluidAudio is a Swift SDK for fully local, low-latency audio AI on Apple devices, with inference offloaded to the Apple Neural Engine (ANE). The SDK includes state-of-the-art speaker diarization, automatic speech recognition, and voice activity detection via open-source models that can be integrated with just a few lines of code."
authors:
  - family-names: "FluidInference Team"
url: "https://github.com/FluidInference/FluidAudio"
repository-code: "https://github.com/FluidInference/FluidAudio"
license: Apache-2.0
version: "0.5.1"
date-released: "2024-12-01"
keywords:
  - "speaker diarization"
  - "automatic speech recognition"
  - "voice activity detection"
  - "apple neural engine"
  - "coreml"
  - "swift"
  - "ios"
  - "macos"
  - "real-time audio processing"
  - "local ai"
  - "privacy-first"
preferred-citation:
  type: software
  title: "FluidAudio: Local Speaker Diarization, ASR, and VAD for Apple Platforms"
  authors:
    - family-names: "FluidInference Team"
  url: "https://github.com/FluidInference/FluidAudio"
  year: 2024
  version: "0.5.1"
references:
  - type: software
    title: "pyannote.audio: neural building blocks for speaker diarization"
    authors:
      - family-names: "Bredin"
        given-names: "Hervé"
    url: "https://github.com/pyannote/pyannote-audio"
  - type: software
    title: "sherpa-onnx: Next-gen Kaldi for speech-to-text, text-to-speech, and speaker recognition"
    url: "https://github.com/k2-fsa/sherpa-onnx"
  - type: software
    title: "Silero VAD: pre-trained enterprise-grade Voice Activity Detector"
    url: "https://github.com/snakers4/silero-vad"
  - type: software
    title: "Parakeet-MLX: Apple MLX implementation of Parakeet TDT models"
    url: "https://github.com/senstella/parakeet-mlx"