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.
audio macos swift ios real-time avfoundation nvidia vad automatic-speech-recognition speech-to-text ane speaker-recognition asr speaker-diarization voice-activity-detection coreml speaker-identification speaker-embedding parakeet
-
Updated
Oct 27, 2025 - Swift