v0.1.0

AIPentest/CyberStrikeAIv0.1.0Aug 19, 2026by pskrunner14

AI Summary

v0.1.0 is the first versioned release of NeMo-Speech.cpp, introducing a comprehensive toolkit for speech processing tasks including recognition, synthesis, and translation.

Key Highlights

  • Support for multiple speech recognition models (Nemotron 3.5, Parakeet) and streaming capabilities.
  • Native C API and OpenAI-compatible HTTP API for seamless application integration.
  • Cross-platform support for Linux, Windows, and macOS with diverse backends including CUDA and Metal.
  • Unified CLI for model discovery, downloads, and caching.

New Features

  • Speech recognition with Nemotron 3.5 ASR and Parakeet models
  • Speaker diarization using Streaming Sortformer v2
  • Text-to-speech synthesis with MagpieTTS
  • Text and speech translation with Riva Translate 4B Instruct v2
  • Post-processing features including VAD, punctuation, and capitalization
  • OpenAI-compatible HTTP API and realtime WebSocket transcription
  • Native C API and CMake package support
  • Backend support for CPU, CUDA, Vulkan, and Metal

Full Release Notes

`0.1.0` is the first versioned release of NeMo-Speech.cpp.

  ## Highlights

  - Speech recognition with Nemotron 3.5 ASR, Nemotron Speech Streaming, Parakeet TDT, and Parakeet CTC
  - Speaker diarization with Streaming Sortformer v2, standalone or integrated with ASR
  - Speech synthesis with MagpieTTS and NanoCodec
  - Text and speech translation with Riva Translate 4B Instruct v2
  - Subtitles, VAD, endpointing, punctuation, capitalization, and structured output
  - Unified nemo-speech CLI with managed model discovery, downloads, and caching
  - Local HTTP API with OpenAI-compatible transcription and speech subsets, realtime WebSocket transcription, and playground
  - Native C API, shared libraries, and exported CMake package for application integration
  - CPU, CUDA, Vulkan, and Metal backend support

Prebuilt archives cover Linux and Windows on x86-64 and ARM64, plus Apple Silicon macOS, using the platform-appropriate CPU, CUDA, Vulkan, or Metal backend.

Note: this is an early release and API interfaces may evolve.