🟩 NVIDIA's whole speech stack just went local. ASR + TTS + codec, quantized to GGUF, running on-device via NeMo-Speech.cpp
Summary
NVIDIA's entire speech stack—ASR, TTS, and codec—is now quantized to GGUF and runs locally on-device via NeMo-Speech.cpp, with new model releases for Magpie-TTS, Nemotron Speech Streaming, and Parakeet.
Similar Articles
I ported NVIDIA Parakeet (speech-to-text) to ggml: same output as NeMo, faster, GGUF-quantized, no Python
NVIDIA's Parakeet speech-to-text models have been ported to pure C++/ggml, achieving byte-identical output to NeMo, up to 5x faster inference on GPU, and quantized GGUF variants for efficient deployment anywhere without Python or PyTorch.
@HuggingApps: NVIDIA Nemotron just dropped an audio-native model that hears the world, not just words transcription, translation, sou…
NVIDIA released Nemotron, an audio-native model capable of transcription, translation, sound recognition, audio Q&A, TTS, and full speech-to-speech, with open weights in 2B and 30B sizes.
@kwindla: https://x.com/kwindla/status/2062544580105359686
NVIDIA released Nemotron 3.5 ASR, an open-source multilingual speech-to-text model with the lowest latency tested, available in multilingual and English-only variants, ideal for voice agents and self-hosted deployments.
@DataChaz: @NVIDIA just quietly dropped an incredibly impressive speech recognition model that completely changes the math for loc…
NVIDIA quietly released Nemotron-3.5-ASR, a lightweight 0.6B parameter open-source speech recognition model designed for real-time streaming with support for 40+ languages, low latency, and cache-aware architecture.
Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS
NVIDIA announces Magpie Multilingual TTS, an open-weights text-to-speech model supporting 12 languages with low-latency deployment via NVIDIA NIM for building production voice agents.