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.

活跃维护 Apache 2.0 Swift Notable
3.2k 492 1 天前
CI
coreml ios macos speaker-diarization speaker-embedding speaker-identification speaker-recognition swift audio avfoundation real-time vad voice-activity-detection asr automatic-speech-recognition speech-to-text parakeet ane nvidia
GitHub 项目主页 对比

星标趋势

数据积累中，暂无足够数据生成趋势图

AI 分析

项目摘要

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.

为什么值得关注

Growing community with 3,201 stars, active contributor community (83 contributors), frequent releases.

优势

  • Continuous integration configured
  • Open source (Apache-2.0)
  • Regular release cadence

局限性

  • No visible test suite
  • Limited documentation
分析模型：fallback | 分析时间：刚刚