← Latest products

FluidAudio

Swift Speaker Diarization on CoreML. 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. We needed a speaker diarization solution that could run every few seconds alongside transcription on iOS and macOS.

DesktopMobileOpen source

3,251 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Dia TTS

    diatts.com

    open-source multi-speaker dialogue generator

    Hacker News6 pts

  2. Audiopipe

    github.com

    Pipeline for audio diarization, denoising and transcription

    Hacker News7 pts

  3. Ghost Pepper Meet local meeting transcription and diarization

    matthartman.github.io

    Voice dictation and meeting transcription without data ever leaving your machine. 100% local models, 100% privacy. Free and open source.

    Hacker News27 pts

  4. Yap

    github.com

    OSS on-device voice dictation for macOS with no model to download

    Hacker News104 pts

  5. EdgeSpeech

    github.com

    on-device speech-to-speech for React Native

    Hacker News5 pts