Skip to content
@Otosaku

Otosaku DSP

Privacy-first AI that works anywhere. We create on-device machine learning libraries optimized for real-time inference — no cloud, no latency, no compromise.

Pinned Loading

  1. OtosakuKWS-iOS OtosakuKWS-iOS Public

    Lightweight on-device keyword spotting engine for iOS using CoreML and real-time audio streaming.

    Swift 16 2

  2. OtosakuStreamingASR-iOS OtosakuStreamingASR-iOS Public

    OtosakuStreamingASR-iOS is a real-time speech recognition engine for iOS, built with Swift and Core ML. It uses a fast and lightweight streaming Conformer model optimized for on-device inference. D…

    Swift 14 4

  3. OtosakuTTS-iOS OtosakuTTS-iOS Public

    Swift library for offline text-to-speech synthesis on iOS/macOS. Generate natural speech directly on device using CoreML-optimized FastPitch and HiFiGAN models. No internet required, fully private.

    Swift 63 9

  4. NeMoConformerASR-iOS NeMoConformerASR-iOS Public

    On-device speech-to-text for iOS/macOS powered by NVIDIA NeMo Conformer CTC Small (13M params). Pure Swift + CoreML implementation with automatic audio padding, chunking for long audio, and real-ti…

    Swift 19

  5. NeMoSpeaker-iOS NeMoSpeaker-iOS Public

    Swift library for Speaker Embedding extraction and verification using NVIDIA NeMo TitaNet model converted to CoreML. Extract 192-dim speaker embeddings, verify speakers, and perform real-time speak…

    Swift 4

  6. NeMoVAD-iOS NeMoVAD-iOS Public

    Swift library for Voice Activity Detection (VAD) using NVIDIA NeMo MarbleNet model converted to CoreML. Detect speech segments in real-time on iOS/macOS with high accuracy and low latency.

    Swift 2

Repositories

Showing 10 of 13 repositories
  • NeMoVAD-iOS Public

    Swift library for Voice Activity Detection (VAD) using NVIDIA NeMo MarbleNet model converted to CoreML. Detect speech segments in real-time on iOS/macOS with high accuracy and low latency.

    Otosaku/NeMoVAD-iOS's past year of commit activity
    Swift 2 0 0 0 Updated Jun 4, 2026
  • NeMoConformerASR-Android Public

    Kotlin library for on-device speech recognition using NVIDIA NeMo Conformer CTC model with ONNX Runtime

    Otosaku/NeMoConformerASR-Android's past year of commit activity
    Kotlin 2 0 0 0 Updated Jun 4, 2026
  • NeMoConformerASR-iOS Public

    On-device speech-to-text for iOS/macOS powered by NVIDIA NeMo Conformer CTC Small (13M params). Pure Swift + CoreML implementation with automatic audio padding, chunking for long audio, and real-time recognition.

    Otosaku/NeMoConformerASR-iOS's past year of commit activity
    Swift 19 0 0 0 Updated Jun 4, 2026
  • OtosakuStreamingASR-iOS Public

    OtosakuStreamingASR-iOS is a real-time speech recognition engine for iOS, built with Swift and Core ML. It uses a fast and lightweight streaming Conformer model optimized for on-device inference. Designed for developers who need efficient audio transcription on mobile.

    Otosaku/OtosakuStreamingASR-iOS's past year of commit activity
    Swift 14 4 1 0 Updated Jun 4, 2026
  • KokoroTTS-iOS Public

    Swift Package for on-device text-to-speech (TTS) on iOS using Kokoro model.

    Otosaku/KokoroTTS-iOS's past year of commit activity
    Swift 2 0 2 0 Updated Mar 2, 2026
  • NeMoFeatureExtractor-Android Public
    Otosaku/NeMoFeatureExtractor-Android's past year of commit activity
    Kotlin 1 0 0 0 Updated Feb 12, 2026
  • NeMoSpeaker-iOS Public

    Swift library for Speaker Embedding extraction and verification using NVIDIA NeMo TitaNet model converted to CoreML. Extract 192-dim speaker embeddings, verify speakers, and perform real-time speaker diarization on iOS/macOS.

    Otosaku/NeMoSpeaker-iOS's past year of commit activity
    Swift 4 0 0 0 Updated Feb 9, 2026
  • NeMoFeatureExtractor-iOS Public
    Otosaku/NeMoFeatureExtractor-iOS's past year of commit activity
    Swift 2 0 0 0 Updated Feb 6, 2026
  • fastpitch-hifigan-coreml-converter Public
    Otosaku/fastpitch-hifigan-coreml-converter's past year of commit activity
    Python 2 0 0 0 Updated Aug 11, 2025
  • OtosakuTTS-iOS Public

    Swift library for offline text-to-speech synthesis on iOS/macOS. Generate natural speech directly on device using CoreML-optimized FastPitch and HiFiGAN models. No internet required, fully private.

    Otosaku/OtosakuTTS-iOS's past year of commit activity
    Swift 63 9 4 1 Updated Aug 11, 2025
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.