v0.1.0

feyninc/pulpiev0.1.0Aug 19, 2026by pskrunner14

AI Summary

v0.1.0 marks the initial release of NeMo-Speech.cpp, providing a unified toolkit for speech recognition, synthesis, and translation. It features support for multiple AI models and backends across various platforms.

Key Highlights

Support for multiple speech recognition models including Nemotron 3.5 ASR, Parakeet TDT, and Parakeet CTC.
Comprehensive speech processing pipeline featuring synthesis (MagpieTTS), translation (Riva Translate), and speaker diarization.
Cross-platform backend support for CPU, CUDA, Vulkan, and Metal on Linux, Windows, and macOS.
Developer integration options including a native C API, OpenAI-compatible HTTP server, and unified CLI tools.

New Features

Nemotron 3.5 ASR and Nemotron Speech Streaming
Parakeet TDT and Parakeet CTC
Streaming Sortformer v2 for speaker diarization
MagpieTTS and NanoCodec for speech synthesis
Riva Translate 4B Instruct v2 for translation
VAD, endpointing, punctuation, and capitalization
Unified nemo-speech CLI with model discovery and caching
Local HTTP API with OpenAI-compatible transcription
Realtime WebSocket transcription
Native C API and CMake package support

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.