#170 · Primary category: Speech & Audio
SwiftWhisper
🎤 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
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production