Articles

Superwhisper

Superwhisper achieved 2x increase in their Free Trial to Pro conversion rate after upgrading their default onboarding to use Parakeet powered by Argmax. Read the blog to understand how Argmax differentiates implementation of open-source model inference.

January 21, 2026

Customer

January 7, 2026

Product

Customize Speech-to-Text for Healthcare

Transcribing medical conversations requires continual adaptation to newly developed medications, tests, procedures, and the unique vocabulary of more than 135 medical specialties—something general-purpose systems are not useful for. Argmax enables real-time, self-serve customization through Custom Vocabulary, where updating system vocabulary is a configuration change rather than a model or system update. Read the blog for details to test this on your iPhone in under 5 minutes.

December 17, 2025

Product

Argmax SDK 2

We are announcing the next major generation of Argmax SDK with a renewed commitment to open-source and a major new Pro-only feature: Real-time Transcription with Speakers!

December 9, 2025

Customer

Detail

Detail, Apple's pick for iPad App of the Year 2025, leverages Argmax SDK to build their flagship AI features such as text-based video editing and automatic speaker switching using Argmax SDK, migrating from cloud APIs.

November 19, 2025

Product

Customize Speech-to-Text

Argmax Pro SDK now supports Custom Vocabulary, an advanced feature that lets developers quickly customize or personalize speech-to-text models by providing a list of contextual keywords at runtime.

November 12, 2025

Customer

ModMed

ModMed selected Argmax to deploy their state-of-the-art medical specialty-tuned speech recognition model for real-time on-device transcription with Argmax Enterprise SDK. Read the case study to learn more about the first 6 months in production and how ModMed CEO views the partnership.

November 10, 2025

Customer

Heidi Health

Heidi Health selected Argmax Enterprise SDK to power their popular AI medical scribe application. Read the case study to learn more about how Heidi collaborated with Argmax to deploy their state-of-the-art model on-device.

September 21, 2025

Benchmarks

iPhone 17

Apple has redesigned the iPhone for the on-device AI age.

August 17, 2025

Research

Interspeech 2025

Argmax is a research-driven on-device AI developer tools company. At Interspeech 2025, Argmax had an oral presentation at the Speaker Diarization track, highlighting the leading speed and accuracy of SpeakerKit.

August 8, 2025

Product

Argmax Local Server

Argmax Local Server brings the state-of-the-art on-device AI capabilities of Argmax SDK to an even wider market without SDK-level integration! The server is ideal for apps migrating from cloud APIs for real-time transcription and feature-complete for AI Meeting Notes apps.

July 24, 2025

Product

Argmax Pro SDK

Argmax Pro SDK is now generally available with best-in-market real-time transcription latency of 160 ms with Nvidia's Parakeet v2 models, orders of magnitude better cost efficiency compared to leading cloud APIs and more!

July 18, 2025

Research

ICML 2025

Argmax is a research-driven on-device AI developer tools company. At ICML 2025, Argmax gave a talk at the On-device AI workshop called WhisperKit: On-device Real-time ASR with Billion-Scale Transformers

June 23, 2025

Partnership

pyannoteAI on Argmax SDK

Argmax partners with pyannoteAI, the industry-leading speaker recognition technology company. pyannoteAI's flagship commercial model is now available for on-device deployment with Argmax SDK. Our Interspeech 2025 paper shows that pyannoteAI's models are industry-leading in speaker diarization accuracy. When combined with Argmax Pro SDK's inference efficiency, the resulting product is the fastest and most accurate on the market.

June 20, 2025

Benchmarks

Apple SpeechAnalyzer and Argmax WhisperKit

Apple introduced SpeechAnalyzer at WWDC 2025 to modernize its on-device speech recognition frameworks. In this post, we share speech-to-text accuracy and speed benchmarks for this new Apple API and compare it to Argmax products on feature set, deployment considerations and more to help developers compare different offerings on the market.

June 19, 2025

Product

Nvidia Frontier Speech Models on Argmax SDK

Argmax SDK now supports the latest Nvidia speech-to-text models such as Parakeet v2, bringing frontier accuracy and unreasonably fast on-device inference to developers. You can test these models in our TestFlight app or sign up to integrate our SDK into your product today!

March 7, 2025

Product

SpeakerKit

Argmax launches SpeakerKit, a state-of-the-art on-device speaker diarization framework with wide compatibility and compact footprint of less than 10 MB.

November 13, 2024

Company

Seed

We've secured an $8 million investment led by Salesforce Ventures, with participation from General Catalyst, Amjad Masad, Julien Chaumond, and other industry leaders.

January 30, 2024

Product

WhisperKit

Argmax has open-sourced WhisperKit in beta under the MIT license, enabling fast and efficient Whisper inference on Apple devices. With a Swift package for easy integration, a sample app on TestFlight, and Python tools for optimization, Argmax aims to bring state-of-the-art automatic speech recognition on device to mainstream.