MacWhisper now highlights individual words during playback if you use a WhisperKit model argmax

WhisperKit Android is now in Beta! WhisperKit is open for business across Android and Apple platforms. Links to code and benchmarks are below in the thread.

Introducing SpeakerKit State-of-the-art on-device speaker diarization: - 10 minutes of audio processed in 3 seconds - 10 megabytes in total - 6-year-old devices supported Details and links to the demo app are in the thread.

Over the last year or so we've been working closely with the team at argmax to improve MacWhisper through WhisperKit. Last week we (finally) released our most requested feature; on-device automatic speaker recognition which is powered by their new SpeakerKit framework.

Great event at OpenAI today giving feedback on their plans for the upcoming open weights model, awesome that they’re involving the on-device developer community from the start 🙌

🔥🔥🔥

Fresh out of the oven 🥖 a bakers dozen of benchmarks for speaker diarization pipelines all in one place

Is on-device the new server-side inference? 👨‍🍳🔜 Vapor

Woah, 3B omni model from Qwen just dropped. This form factor is huge for small devices like phones - one model to rule them all! Hope the other big labs catch on with their upcoming small models 🚀

If you're working on AI, ML, MLX, and/or CoreML on iOS and macOS, you don't want to miss the AiOS meetup I'm co-hosting with Rudrank Riyam on Wed June 11 in Cupertino lu.ma/aios-omt

Everyone is talking about how we need more AI data centers (especially the ones who would mostly benefit from them) but why is no one talking about on-device AI? Running AI on your device: - Free - Faster & takes advantage of existing hardware - 100% privacy and control (you

So many awesome people in one place 🤯 Excited for what’s coming tomorrow #WWDC25

MLX showing up in the developer app 🚀 #WWDC25

Kudos to David Koski! From discussion to merged PR in 2 days. You can't beat open source!

Nvidia model running on Apple Neural Engine 🤯 Excited to ship this - turns out the model is faster and more accurate than a lot of cloud transcription APIs today, and we got it running locally on an iPhone 📲 NVIDIA AI cooked!

During WWDC25, Apple modernized its on-device speech recognition framework with the new SpeechAnalyzer. Many of you asked us to compare it to @openai Whisper and NVIDIA AI's frontier speech models, so we ran the benchmark and compared feature sets! Details below