# argmaxinc/argmax-oss-swift

On-device Speech AI for Apple Silicon

Repository: https://github.com/argmaxinc/argmax-oss-swift
Canonical: https://ross.abutalabs.com/products/argmax-oss-swift
Language: Swift
License: MIT
License Family: permissive
Topics: inference, ios, speech-recognition, swift, whisper, transformers, macos, pyannote, qwen3-tts, speech-to-text, text-to-speech, ttskit, whisperkit, speakerkit, speaker-diarization
Last push: 2026-08-13T19:17:27+00:00

## Health v2 (maintenance only)
Score: 91/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 96, longevity 67
- inputs: {"age_days": 950, "days_push": 20, "days_rel": 27, "gap_med": 30, "n_releases_24m": 18}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6338, forks 600 (observed 2026-08-28T04:09:41.821883+00:00)

## What it is
A Swift SDK providing turn-key on-device speech AI frameworks for Apple Silicon, including WhisperKit (speech-to-text with Whisper), SpeakerKit (speaker diarization with Pyannote), and TTSKit (text-to-speech with Qwen-TTS). It is distributed via Swift Package Manager and Homebrew for iOS and macOS apps.

## Use cases
- transcribe audio to text on-device with whisper
- add speech-to-text to an ios app
- run speaker diarization locally on macos
- convert text to speech on apple devices
- offline transcription without sending audio to a server
- identify who is speaking in a meeting recording

## When to choose
- you need private, fully on-device speech recognition on iOS or macOS
- you are building a Swift app and want drop-in Whisper transcription
- you need speaker diarization or TTS running locally on Apple Silicon

## When to avoid
- you need Android or cross-platform support in the open-source SDK
- you need real-time transcription with speakers or custom vocabulary (Pro SDK features)
- your app is not in the Swift/Apple ecosystem

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, tts, machine-learning, llm-inference, sdk
- domain: speech-processing, machine-learning, apple-ecosystem
- platform: -
- tags: whisperkit, speakerkit, ttskit, on-device-inference, coreml, speaker-diarization, whisper, swift-package, audio, macos, ios, swift, apple-ecosystem

## Member repositories
- argmaxinc/argmax-oss-swift (main) score 91

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:41.821883+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:46:08.951215+00:00, confidence not recorded.
  - readme: https://github.com/argmaxinc/argmax-oss-swift (fetched 2026-08-28T04:09:41.821883+00:00, sha 1d96dd328ad0)
- Data as of 2026-08-30T08:39:29.467469+00:00.