#170 · Primary category: Speech & Audio

SwiftWhisper

ios macos openai speech-recognition speech-to-text swift transcription whisper whisper-cpp

🎤 The easiest way to transcribe audio in Swift

Project last updated:05/23/24

GitHub Stars

786

Forks

107

Contributors

2

License

MIT

Why we included this project

SwiftWhisper is a good fit if you want speech-to-text inside an iOS or macOS app without sending audio to a cloud service. It wraps whisper.cpp in a small Swift API, so loading a Whisper model and transcribing 16kHz PCM audio takes only a couple of lines. The delegate callbacks report new segments, progress, and errors as they happen, which makes it easy to wire into a recording or meeting-notes screen. Since transcription happens on the device, it works offline and keeps sensitive audio local. Setup is a standard Swift Package Manager dependency, and the CoreML support points toward faster inference on Apple silicon.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category