#3838th of 67 in VoiceFor voice, speech and music
argmax-oss-swift
Swift SDK for on-device speech-to-text, diarization and TTS on Apple devices
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 6.4k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Swift
5,836 on 4 Apr 20266,438 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Swift package with three Core ML libraries: WhisperKit for Whisper transcription, SpeakerKit for Pyannote speaker diarization, and TTSKit for Qwen3-TTS speech synthesis. It also ships a CLI and an optional local server that implements the OpenAI Audio API transcription and translation endpoints. Real-time transcription with speakers and Android support are in the separate Pro SDK.
Who it is for: Swift developers adding local speech features to macOS and iOS apps
Strengths
- Runs Whisper, Pyannote and Qwen3-TTS on-device via Core ML, no server required
- Local server exposes /v1/audio/transcriptions and /v1/audio/translations for OpenAI SDK clients
- Incremental loading streams long audio from disk in bounded memory using VAD chunking
- whisperkittools converts and publishes your own fine-tuned Whisper models in Core ML
Weaknesses
- Apple platforms only: macOS 14+ and Xcode 16+; TTSKit needs macOS 15 or iOS 18
- Local server supports only json and verbose_json, no SRT, VTT or plain text
- Server needs a BUILD_ALL=1 build and one model chosen at launch with --model
- Real-time transcription with speakers and custom vocabulary are Pro SDK only
What it needs
- Needs Xcode 16+, macOS 14+, git-lfs (CLI model download)
- Models: OpenAI Whisper (Core ML), Pyannote, Qwen3-TTS 0.6B and 1.7B
- port 50060
Quick answers
Is argmax-oss-swift open source?
Yes. Its code is on GitHub under the MIT license.
Also in Voice
See all 67| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 97 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 89 out of 100 |
| 3 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 89 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 82 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 81 out of 100 |