| --- |
| title: Soniqo |
| emoji: 🎙️ |
| colorFrom: purple |
| colorTo: blue |
| sdk: static |
| pinned: false |
| --- |
| |
| # Soniqo |
|
|
| **Open-source speech AI that runs on-device.** |
|
|
| Soniqo builds local speech models and runtimes for Apple Silicon, iOS, Android, Linux, and Windows: ASR, TTS and voice cloning, VAD, diarization, speech enhancement, and voice-agent pipelines. |
|
|
| [Website & docs](https://soniqo.audio) · [GitHub](https://github.com/soniqo) · [All models](https://huggingface.co/soniqo/models) |
|
|
| ## Model collections |
|
|
| - [ONNX](https://huggingface.co/collections/soniqo/onnx) — cross-platform and Android model bundles |
| - [LiteRT](https://huggingface.co/collections/soniqo/litert) — efficient on-device models for Android, Linux, and Windows |
| - [MLX Speech Models](https://huggingface.co/collections/aufklarer/mlx-speech-models) — optimized for Apple Silicon |
| - [CoreML Speech Models](https://huggingface.co/collections/aufklarer/coreml-speech-models) — optimized for Apple Neural Engine on iOS and macOS |
|
|
| ## Repositories |
|
|
| [speech-swift](https://github.com/soniqo/speech-swift) · [speech-core](https://github.com/soniqo/speech-core) · [speech-android](https://github.com/soniqo/speech-android) · [speech-studio](https://github.com/soniqo/speech-studio) · [runner](https://github.com/soniqo/runner) |
|
|
|
|
