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.
📊 Project Info
- Language
- Swift
- Stars
- ⭐ 2,436
- Forks
- 342
- Today
- +6
- Ranking
- #8
- Collection
- Language
- Trending Date
- July 13, 2026
- Last Push
- 7/12/2026
🏷️ Topics
aneasraudioautomatic-speech-recognitionavfoundationcoremliosmacosnvidiaparakeetreal-timespeaker-diarizationspeaker-embeddingspeaker-identificationspeaker-recognitionspeech-to-textswiftvadvoice-activity-detection
📸 Screenshots
