Checkout our HuggingFace🤗 collection for the latest open weight checkpoints and demos!
NeMo Speech 3.0 is now available as release v3.0.0 and in the 26.07.00 NeMo Speech NGC container. The final NeMo release before the repository split was v2.7.3, available in the 26.04 NeMo NGC container.
- 2026-07: MagpieTTS v2607 has been released with support for 3 new languages (Ar, Ko, Pt) + 9 existing languages (En, Es, De, Fr, Vi, It, Zh, Hi, Ja). Try out the demo!
- 2026-06: Nemotron-3.5-ASR-Streaming-0.6B has been released with 40 languages supported, controllable latency 80ms-1s, and 240-2400 1xH100 concurrent streams. Built on cache-aware Fastconformer architecture.
- 2026-04: Parakeet-unified-en-0.6b has been released with high-quality offline and streaming (with a minimum latency of 160ms) inference in one model for English language with punctuation and capitalization support.
- 2026-03: Nemotron 3 VoiceChat is now released in Early Access. Built on the Nemotron Nano v2 LLM backbone with Nemotron speech and TTS decoder, VoiceChat delivers full-duplex, natural, interruptible conversations with low latency. Try out the demo and apply for early access.
- 2026-03: Nemotron-Speech-Streaming v2603 has been updated. It has been trained on a larger and more diverse corpus, resulting in lower WER across all latency modes. Try out the demo and check out the NIM.
- 2026-03: MagpieTTS v2602 has been released with support for 9 languages (En, Es, De, Fr, Vi, It, Zh, Hi, Ja).
- 2026-01: Nemotron-Speech-Streaming was released: One checkpoint that enables users to pick their optimal point on the latency-accuracy Pareto curve!
- 2026-01: MagpieTTS v2512 was released.
- 2026: This repo has pivoted to focus on audio, speech, and multimodal LLMs. For the final pre-split NeMo release with support for additional modalities, see v2.7.3.
- 2025-08: Parakeet V3 and Canary V2 have been released with speech recognition and translation support for 25 European languages.
- 2025-06: Canary-Qwen-2.5B has been released with record-setting 5.63% WER on English Open ASR Leaderboard.
NVIDIA NeMo Speech is built for researchers and PyTorch developers working on Speech models including Automatic Speech Recognition (ASR), Text to Speech (TTS), and Speech LLMs. It is designed to help you efficiently create, customize, and deploy new AI models by leveraging existing code and pre-trained model checkpoints.
For technical documentation, please see the NeMo Speech Developer Documentation.
NeMo Speech works with the Python, PyTorch, and CUDA versions of your choosing:
- Python 3.12 or above
- PyTorch 2.7 or above (CPU, CUDA, etc. — your choice)
- NVIDIA GPU + CUDA (required for training; recommended for inference)
If you already have a Python/PyTorch/CUDA stack that satisfies those minimums, NeMo Speech installs on top of it without replacing it, so your existing PyTorch build is kept (see the install options below). The versions pinned in uv.lock and shipped in the official container — Python 3.13, PyTorch 2.11 with CUDA 12.9 or PyTorch 2.12 with CUDA 13.2 — are simply the combinations we actively test and support. They make setup turnkey and reproducible, but they are not a hard requirement.
As of Pytorch 2.6,
torch.load defaults to using weights_only=True. Some model checkpoints may require using weights_only=False.
In this case, you can set the env var TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1 before running code that uses torch.load.
However, this should only be done with trusted files. Loading files from untrusted sources with more than weights only
can have the risk of arbitrary code execution.
| Version | Description |
|---|---|
| 3.0.0 (latest release) | NeMo Speech 3.0.0 documentation |
| Nightly | Documentation for the latest main branch |
The recommended way to install NeMo Speech is from source with uv, which reproduces our actively-tested stack from the committed uv.lock. If you need different Python/PyTorch/CUDA versions, NeMo Speech also installs over your existing environment via pip — see the pip fallback below.
git clone https://github.com/NVIDIA-NeMo/Speech.git
cd Speech
uv sync --extra all --extra cu13 # CUDA 13.x (recommended) — use --extra cu12 for CUDA 12.xThis installs our supported stack (Python 3.13, PyTorch 2.12, CUDA 13.2) into .venv/ with NeMo Speech editable. Add --group test for the test suite or --group docs to build the docs; run tools via uv run <cmd> or activate with source .venv/bin/activate. On Linux, cu12 and cu13 are mutually exclusive — pass exactly one (cu13 is the default). For the exact container baseline, add --locked --python 3.13 (the path the Dockerfile and CI use).
SpeechLM2 / Automodel: the Automodel backend runs without any compiled dependencies. It can optionally benefit from dedicated accelerated backends (Transformer Engine, FlashAttention, Mamba, grouped-GEMM/MoE, DeepEP) for better performance — these source-built kernels come from the
compiled(Hopper/Blackwell) orcompiled-a100(A100) extras, built bydocker/Dockerfile(GPU_TARGET=h100plus/a100). See the installation guide for the full list and build details.
The latest prebuilt NeMo Speech image is the 26.07.00 NGC container:
docker pull nvcr.io/nvidia/nemo-speech:26.07.00
docker run --rm -it --gpus all -v "$PWD:/workspace" nvcr.io/nvidia/nemo-speech:26.07.00 bashTo build the container from source (CUDA 13 / H100+ by default):
git clone https://github.com/NVIDIA-NeMo/Speech.git
cd Speech
docker buildx build -f docker/Dockerfile -t nemo-speech . # CUDA 13 / H100+ (default)
docker run --rm -it --gpus all -v "$PWD:/workspace" nemo-speech bashFor A100, set GPU_TARGET=a100 — A100 works with both CUDA 12 and CUDA 13 (CUDA 13, the default base image, is recommended; the CUDA 12 base is a convenience). See the header of docker/Dockerfile for all build arguments (BASE_IMAGE, GPU_TARGET).
Prefer your own Python/PyTorch/CUDA? Install your PyTorch first (any version ≥ 2.7 for your CPU/CUDA/etc. target — see the PyTorch install matrix), then add NeMo Speech and it keeps your build. uv pip (uv's fast, pip-compatible installer) works like pip:
uv pip install 'nemo-toolkit[asr,tts]' # or plain: pip install 'nemo-toolkit[asr,tts]'
⚠️ Do not useuv sync --lockedfor a bring-your-own stack — it appliesuv.lockand replaces your Python/PyTorch/CUDA with the supported baseline. Useuv pip/piphere; reserveuv sync --lockedfor reproducing our stack.
To instead pull our pinned PyTorch build, add the CUDA extra and the matching wheel index (pip/uv pip do not read uv's project index config, so --extra-index-url is required):
pip install 'nemo-toolkit[asr,tts,cu13]' --extra-index-url https://download.pytorch.org/whl/cu132 # CUDA 13.x
pip install 'nemo-toolkit[asr,tts,cu12]' --extra-index-url https://download.pytorch.org/whl/cu129 # CUDA 12.xWe welcome community contributions! Please refer to CONTRIBUTING.md for the process.
NeMo Speech is licensed under the Apache License 2.0.