ทวีตที่ปักหมุด
argmax
309 posts
argmax
@argmax
Frontier Models On Device
Palo Alto, CA เข้าร่วม Kasım 2023
18 กำลังติดตาม4.4K ผู้ติดตาม
Argmax Playground for Android is now available to install and test on your Android phone: appdistribution.firebase.dev/i/76e81fffb213…
English
Our blog post explains the technical breakthroughs and how Argmax became the first SDK to build with LiteRT in collaboration with @GoogleAI argmaxinc.com/blog/argmax-pr…
English
Introducing Real-time Transcription with Nvidia Parakeet on Android!
Argmax Pro now supports Android with our brand-new Kotlin-first SDK, bringing Argmax's top-tier accuracy and real-time performance from Apple to Android.
Enjoying seamless NPU and GPU acceleration by @GoogleAI LiteRT across several major hardware vendors.
Links to blog and test app are in the replies.
English
The latest Argmax Playground is now available on iOS TestFlight! testflight.apple.com/join/Q1cywTJw
argmax@argmax
Real-time Transcription with Speakers is now generally available on iOS and macOS! Details for installing or simply testing Argmax SDK 2 are in the comments.
English
TTSKit is now part of Argmax Open-source SDK!
Get started with the 0.16.0 release: github.com/argmaxinc/Whis…
argmax@argmax
TTSKit now achieves sub-100ms time-to-first-byte for Qwen3-TTS 1.7b on Apple Silicon! Link to the code repo and details in comments.
English
This is achieved by prompt prefix caching, and the framework and app example code is live on GitHub: github.com/argmaxinc/Whis…
From Apple M2 through M5, the empirical range varies from 70ms to 130ms. TTSKit achieves faster-than-real-time playback on M2 and newer. We are working on further speed optimizations to achieve the same on M1.
The next feature is voice cloning!
English
TTSKit now achieves sub-100ms time-to-first-byte for Qwen3-TTS 1.7b on Apple Silicon!
Link to the code repo and details in comments.
argmax@argmax
We are open-sourcing TTSKit! Run state-of-the-art text-to-speech models on your Mac and iPhone. The launch version supports @Alibaba_Qwen Qwen3-TTS and generates audio faster than real-time playback with sub-200 ms time-to-first-byte. Voice cloning and advanced speed optimizations will be in the next version. Link to the GitHub repo and models on @huggingface in comments.
English
argmax รีทวีตแล้ว
On-device inference is not limited to one model at a time, but orchestration is critical!
Here is a concurrency load test for running 4 leading models in real-time totalling 3 billion parameters on Apple Neural Engine:
- Qwen3-TTS (1.7b)
- Parakeet v2 (0.6b)
- Canary v2 (0.6b)
- Sortformer (0.1b)
English
Argmax Playground 2.0.3 is still under review by Apple. We will announce its availability as soon as it is published to TestFlight: testflight.apple.com/join/Q1cywTJw
English
Real-time Transcription with Speakers is now generally available on iOS and macOS!
Details for installing or simply testing Argmax SDK 2 are in the comments.
argmax@argmax
Introducing Real-time Transcription with Speakers! - Step change in accuracy, surpassing top cloud APIs - Faster than real-time on Mac and iPhone - Still under 3 watts when all features are enabled Available in Argmax SDK 2.0 for early access! Benchmarks and details in comments.
English
@argmax @Alibaba_Qwen Why is everything apple first? I have a windows and android. I feel sad!
English
We are open-sourcing TTSKit!
Run state-of-the-art text-to-speech models on your Mac and iPhone.
The launch version supports @Alibaba_Qwen Qwen3-TTS and generates audio faster than real-time playback with sub-200 ms time-to-first-byte.
Voice cloning and advanced speed optimizations will be in the next version. Link to the GitHub repo and models on @huggingface in comments.
English
Argmax now has two open-source kits: WhisperKit and TTSKit. It will be three before March.
We will consolidate these Kits under a single Argmax Open-source SDK and demonstrate the compounding value of using multiple Kits to solve challenging tasks such as voice agents and content readers.
English
TTSKit is in preview, with a turnkey example app you can build locally in Xcode. Go try it out and let us know how it went! github.com/argmaxinc/Whis…
English
Hundreds of thousands use @superwhisper to transcribe messages, meetings, AI prompts, and more every day across iOS and macOS.
Superwhisper achieved a 2x increase in their Free Trial to Pro conversion rate after upgrading their default onboarding to Parakeet powered by Argmax.
Read the case study to learn more about leveraging on-device inference as a profit center instead of a cost-savings solution.
English
Run state-of-the-art speech-to-text on Apple Silicon: github.com/argmaxinc/Whis…
English
We are thrilled that WhisperKit reached 1 million monthly on @huggingface!
- First ever Apple Silicon-only model to reach 1M
- Usage grew 10x in 2025
- Free, MIT open-source and pure-Swift
English