Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
| Date | Stars |
|---|---|
| 2026-07-24 | 1075 |
| 2026-07-25 | 1078 |
| 2026-07-28 | 1078 |
| 2026-07-30 | 1078 |
| 2026-08-06 | 1078 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
45.0
growth rate 0.00%/day
# Speech Swift
AI speech models for Apple Silicon, powered by MLX Swift and CoreML.
📖 Read in: [English](README.md) · [中文](README_zh.md) · [日本語](README_ja.md) · [한국어](README_ko.md) · [Español](README_es.md) · [Deutsch](README_de.md) · [Français](README_fr.md) · [हिन्दी](README_hi.md) · [Português](README_pt.md) · [Русский](README_ru.md) · [العربية](README_ar.md) · [Tiếng Việt](README_vi.md) · [Türkçe](README_tr.md) · [ไทย](README_th.md)
On-device speech recognition, synthesis, and understanding for Mac and iOS. Runs locally on Apple Silicon — no cloud, no API keys, no data leaves your device.
**[📚 Full Documentation →](https://soniqo.audio)** · **[🤗 HuggingFace Models](https://huggingface.co/aufklarer)** · **[📝 Blog](https://blog.ivan.digital)** · **[💬 Discord](https://discord.gg/TnCryqEMgu)**
<p align="center">
<a href="https://formulae.brew.sh/formula/speech"><img src="https://img.shields.io/homebrew/installs/dm/speech.svg?logo=homebrew&label=Homebrew%20installs&color=FBB040" alt="Homebrew installs"></a>
<a href="https://github.com/soniqo/speech-swift#built-with-speech-swift"><img src="https://img.shields.io/badge/verified%20public%20repositories-15-2ea44f?logo=github" alt="Verified public repositories: 15"></a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/24196?utm_source=trendshift-badge&utm_medium=badge&utm_campaign=badge-trendshift-24196" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/24196/daily?language=Swift" alt="soniqo%2Fspeech-swift | Trendshift" width="250" height="55"/></a>
</p>
<p align="center">
<a href="https://youtu.be/x9zgcaW0gUk">
<img src="https://img.youtube.com/vi/x9zgcaW0gUk/maxresdefault.jpg" width="640" alt="Local Speech AI on a MacBook — watch the 4-minute open-source library tour on YouTube">
</a>
</p>
<p align="center"><em>Local Speech AI on a MacBook — watch the 4-minute open-source library tour on YouTube</em></p>
**Use cases:** [Voice Agents](https://soniqo.audio/voice-agents) · [Transcription](https://soniqo.audio/transcription) · [Speech Generation](https://soniqo.audio/speech-generation)
## Built with Speech Swift
15 public repositories with verifiable Speech Swift package references.
[Palmier Pro](https://github.com/palmier-io/palmier-pro) · [Anarlog](https://github.com/fastrepl/anarlog) · [ClawdHome](https://github.com/ThinkInAIXYZ/clawdhome) · [Jabber](https://github.com/rselbach/jabber) · [Ora](https://github.com/wuwangzhang1216/ora) · [VoxFlow](https://github.com/xingbofeng/VoxFlow) · [LokalBot](https://github.com/stevyhacker/lokalbot) · [Voicey](https://github.com/jonathanKingston/voicey) · [HushType](https://github.com/felixfu824/HushType) · [DexDictate macOS](https://github.com/westkitty/DexDictate_MacOS) · [Watchtower](https://github.com/aiwatchtowers/watchtower) · [Wishper App](https://github.com/irangareddy/wishper-app) · [FriSpeak](https://github.com/KSubedi/FriSpeak) · [Scribe](https://github.com/itchat/Scribe) · [VoicePen](https://github.com/dot-sk/VoicePen)
**OpenAI-compatible apps:** [AnythingLLM](https://github.com/Mintplex-Labs/anything-llm) ([merged WAV support](https://github.com/Mintplex-Labs/anything-llm/pull/6012))
**Capability groups:** STT / ASR · Alignment · TTS · LLMs & translation · Speech-to-speech · Enhancement/restoration · Source separation · Music/audio generation · Wake word, VAD, diarization & speaker identity
**STT / ASR**
- **[Qwen3-ASR](https://soniqo.audio/guides/transcribe)** — Speech-to-text (automatic speech recognition, 52 languages, MLX + CoreML)
- **[WhisperASR](docs/models/whisper-asr.md)** — Whisper Large-v3 Turbo speech-to-text via native CoreML runtime (ANE, multilingual)
- **[MOSS Transcribe Diarize](https://soniqo.audio/guides/moss)** — Native CoreML/MLX offline transcription with model-generated speaker labels and timestamps (128K MLX context; INT5/INT8)
- **[Parakeet TDT](https://soniqo.audio/guides/parakeet)** — Excerpt of 39,723 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:52c4b6dac3268a86, topic:speech-recognition, topic:text-to-speech, topic:tts
