soniqo / speech-swift
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
Why this job: topics: text-to-speech, tts, speech-recognition, asr, tts
What it does
AI speech models for Apple Silicon, powered by MLX Swift and CoreML.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 11 days ago
- Stars
- 1,266
- +3 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- Mac
- From the latest release
- Latest version
- v0.0.29
- Released 16 days ago
- Built with
- Swift
- 97% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 94% closed
- 7 still open
- Pull requests
- 396 merged
- 10 waiting
- Releases
- 29
- 29 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Neywa-Labs / mlx-audio | 8,224 | today | MIT | No downloads |
| argmaxinc / argmax-oss-swift | 6,448 | 30 days ago | MIT | No downloads |
| espnet / espnet | 10,010 | yesterday | Apache-2.0 | No downloads |
More: download files, languages, topics and project record
Languages
- Swift 97%
- Python 2%
- C++ <1%
- Shell <1%
Topics
- apple-silicon
- asr
- coreml
- ios
- macos
- mlx
- neural-engine
- on-device
- speaker-diarization
- speech-enhancement
- speech-recognition
- speech-to-speech
Project record
- JobSpeech and audio
- StatusListed
- Commits1,082
- Forks189
- Watching10
- Stars in 28 days+36
- CreatedFeb 4, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026