Back: Catalog

argmax-oss-swift

This open-source software kit offers built-in AI-based speech processing capabilities on Apple Silicon devices. OpenAI supports audio text conversion with Whisper, speaker separation with Pyannote, and text voiceover with Qwen-TTS. You can integrate it into your projects through Swift Package Manager.

AR

argmax-oss-swift

New80

argmaxinc · Voice & Text-to-Speech

STARS6.4K
FORKS624
COMMITS0
CONTRIBUTORS0
VERSIONv1.1.0
UPDATED3 days ago
SwiftSpeech AIWhisperTTSKitMIT

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • You can convert sounds to text using the OpenAI Whisper model.
  • With the Pyannote infrastructure, you can distinguish speakers in audio recordings.
  • You can convert text to audio using Qwen-TTS.
GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech