Practical overview
When it fits
Use it when adding one or more of the listed speech tasks to an Apple-platform Swift project and on-device inference is relevant.
Who it is for
- Swift developers building iOS or macOS applications with speech features.
- Teams choosing between speech transcription, speaker diarization and text-to-speech components.
Documented uses
- Transcribe local audio files in a Swift project.
- Identify speakers in audio.
- Generate speech from text.
Requirements & limits
The repository is public and lists an MIT license. The documented Xcode setup requires macOS 14.0 or later and Xcode 16.0 or later.
- WhisperKit, SpeakerKit and TTSKit address different tasks and can be selected individually.
- The README describes the frameworks as on-device inference for Apple Silicon.
- The open-source package is distinct from Argmax Pro SDK; the README lists additional features and Android support under Pro.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Add the speech libraries to an Xcode project
Include the SDK’s umbrella product or selected speech libraries as package dependencies.
Before you start
- A Swift project in Xcode
- macOS 14.0 or later
- Xcode 16.0 or later
Steps
Open the Swift project in Xcode and choose File > Add Package Dependencies.
Enter https://github.com/argmaxinc/argmax-oss-swift and select a version range or specific version.
Choose ArgmaxOSS to include all kits, or select WhisperKit, TTSKit or SpeakerKit as needed.
Expected outcome
The selected products are added to the project as Swift package dependencies.
Guide limitations
- This covers package setup; the selected product’s own documentation is needed for implementation details.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 13 October 2026
- Original website title
- argmaxinc/argmax-oss-swift · Official homepage title · retained in its source language