speechbrain
All-in-one speech toolkit in pure Python and Pytorch
Decision gist · record as of 2026-08-14
Yes. SpeechBrain is actively maintained, permissively licensed, and has low installation friction. It is well-suited for anyone building speech or text processing systems in Python, whether for research, prototyping, or production inference. The extensive pretrained model library and training recipes reduce development time significantly. Choose it if you need a unified toolkit spanning multiple speech/text tasks; avoid it only if you require a narrowly specialized tool for a single task.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires PyTorch and torchaudio; downloading pretrained models requires internet access and disk space for model storage.
- Installation is straightforward via PyPI with low friction.
- The package maintains active status and depends on well-established libraries (torch, torchaudio, numpy, scipy, soundfile) that are standard in ML workflows.
License · maintenance · safety
Apache-2.0 (permissive) — Licensed under Apache-2.0 (permissive), allowing commercial use, modification, and distribution with minimal restrictions. You may use this in proprietary projects provided you include a copy of the license and state significant changes.
last release 2026-03-31 (136 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,759,440 downloads/mo, #3,586 on PyPI
Alternatives
Verify before relying
pip install speechbrain
from speechbrain.inference import EncoderDecoderASR
asr_model = EncoderDecoderASR.from_hparams(
source="speechbrain/asr-conformer-transformerlm-librispeech",
savedir="pretrained_models/asr-transformer-transformerlm-librispeech"
)
asr_model.transcribe_file("example.wav")- Whether all 100+ pretrained models mentioned in the description are actively maintained and accessible.
- Performance benchmarks or accuracy metrics for the supported tasks relative to other frameworks.
- Whether EEG modality support is production-ready or still experimental.
What it is and what it does
SpeechBrain is an open-source PyTorch toolkit designed to accelerate development of conversational AI systems. It provides a unified framework for speech and text processing tasks including speech recognition, speaker recognition, speech enhancement, speech separation, language modeling, and dialogue systems. The toolkit ships with over 100 pretrained models hosted on HuggingFace and supports both inference and training workflows.
The package is structured around training recipes—YAML-based hyperparameter configurations paired with Python training scripts—that allow you to train models from scratch or fine-tune existing pretrained models like Whisper, Wav2Vec2, and Llama2. It includes extensive documentation and tutorials aimed at researchers, practitioners, and students. Core dependencies are torch, torchaudio, numpy, scipy, and huggingface_hub, making it suitable for environments already set up for deep learning work.
Use it for
- Build and deploy automatic speech recognition systems using pretrained Conformer or Transformer models with minimal code.
- Fine-tune pretrained models like Whisper or Wav2Vec2 on custom datasets using provided training recipes.
- Implement speech enhancement or speaker separation pipelines for audio preprocessing in production systems.
- Accelerate research by comparing new model architectures against established baselines across 40+ datasets.
- Teach conversational AI and speech processing concepts using tutorials and documented examples in academic settings.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
SpeechBrain is actively maintained, permissively licensed, and has low installation friction. It is well-suited for anyone building speech or text processing systems in Python, whether for research, prototyping, or production inference. The extensive pretrained model library and training recipes reduce development time significantly. Choose it if you need a unified toolkit spanning multiple speech/text tasks; avoid it only if you require a narrowly specialized tool for a single task.
Install
speechbrain on PyPI
Before you install
Installation is straightforward via PyPI with low friction. The package maintains active status and depends on well-established libraries (torch, torchaudio, numpy, scipy, soundfile) that are standard in ML workflows. No unusual system dependencies or compatibility concerns are evident from the fact sheet.
Requires PyTorch and torchaudio; downloading pretrained models requires internet access and disk space for model storage.
License in practice
Licensed under Apache-2.0 (permissive), allowing commercial use, modification, and distribution with minimal restrictions. You may use this in proprietary projects provided you include a copy of the license and state significant changes.
Quickstart
pip install speechbrain
from speechbrain.inference import EncoderDecoderASR
asr_model = EncoderDecoderASR.from_hparams(
source="speechbrain/asr-conformer-transformerlm-librispeech",
savedir="pretrained_models/asr-transformer-transformerlm-librispeech"
)
asr_model.transcribe_file("example.wav")Verify before relying
- Whether all 100+ pretrained models mentioned in the description are actively maintained and accessible.
- Performance benchmarks or accuracy metrics for the supported tasks relative to other frameworks.
- Whether EEG modality support is production-ready or still experimental.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.8.1 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 12 packageshyperpyyamljoblibnumpypackagingrequestsscipysentencepiecesoundfiletorchtorchaudiotqdmhuggingface_hub |
| Maintenance | Actively maintained 136 days since the last release |
| First released | |
| Downloads | 1,759,440 / month, #3,586 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3 |
Evidence: speechbrain-1.1.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “speech recognition toolkit”
- speechbrainSpeechBrain is a PyTorch-based toolkit for building speech and text…
- nemo-toolkitnemo-toolkit provides a PyTorch framework for building, training, and…
- funasrFunASR is a speech recognition toolkit that transcribes audio offline…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also pyctcdecode · TTS · nemo-toolkit · laion-clap · pyannote-audio · panns-inference · sherpa-onnx-core · deepfilternet · coqui-tts · Resemblyzer