SpeechBrain
All-in-one conversational AI toolkit for ASR, speaker recognition, speech enhancement, and language identification.
SpeechBrain
SpeechBrain is an open-source, all-in-one conversational AI platform developed at Mila and Université de Montréal. A single, modular codebase covers automatic speech recognition, speaker recognition and diarisation, speech enhancement and separation, language identification, and spoken language understanding.
Key Features
- 200+ pretrained models on HuggingFace Hub across all speech tasks
- Modular Brain class: compose any pipeline from reusable blocks
- State-of-the-art ASR with Transformer, Conformer, and hybrid CTC/attention
- Speaker verification and identification (ECAPA-TDNN, x-vectors)
- Speech enhancement: MetricGAN+, SEGAN, and ConvTasNet separation
Quick Start
pip install speechbrain
import speechbrain as sb
from speechbrain.inference.ASR import EncoderDecoderASR
asr_model = EncoderDecoderASR.from_hparams(
source="speechbrain/asr-conformer-transformerlm-librispeech",
savedir="pretrained_models/asr-transformer-transformerlm-librispeech",
)
result = asr_model.transcribe_file("audio.wav")
print(result)
npx ai-supply add speechbrain-audio-toolkit
Curated mirror of the open-source SpeechBrain (Apache-2.0). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/speechbrain-audio-toolkit/check). Click a policy:
Consume SpeechBrain programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/speechbrain-audio-toolkit
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/speechbrain-audio-toolkit/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add speechbrain-audio-toolkit
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/speechbrain-audio-toolkit/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "speechbrain-audio-toolkit" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.