01
AI Foundations
Understand what AI is, how systems learn, where they fail, and how to judge claims without hype.
Free AI library
Audio AI guidesFree forever.
117 plain-English guides, structured learning paths, and an open library — built by an independent 501(c)(3) nonprofit so anyone can understand modern AI.
117Free guides
1Topic tracks
~2 minPer guide
~4hReading time
Start here
Five outcome-based courses
Each course includes explicit outcomes, mapped competencies, practice activities, and an applied capstone.
02
Responsible AI User
Use AI productively while protecting privacy, checking outputs, and preserving human accountability.
03
AI at Work
Evaluate workplace use cases, run safe pilots, measure value, and communicate changes responsibly.
04
AI Policy & Society
Analyze AI systems through rights, equity, governance, safety, and public-interest outcomes.
05
Building with AI Systems
Understand language models, retrieval, agents, evaluation, cost, and deployment safeguards through practical system design.
Topic tracks
Browse by track
Jump into the area you care about. Every track has multiple plain-English guides.
FundamentalsCore concepts: how AI works at a high level.84 guides Language AILLMs, NLP, ChatGPT, prompting, and text understanding.155 guides Visual AIImage generation, computer vision, video, and design.133 guides Audio AIVoice, music, podcasting, and audio-first AI.117 guides CompaniesProfiles of OpenAI, Anthropic, Google, Meta, and more.121 guides ApplicationsHow AI shows up in coding, search, agents, and daily life.111 guides IndustriesAI in healthcare, finance, education, energy, and more.91 guides TechnicalChips, fine-tuning, RAG, vectors, and AI infrastructure.177 guides SocietyBias, privacy, copyright, safety, and the AI future.30 guides
Full library
All guides
117 of 1019 guides shown. Filter by track or search above.
Audio AI
Mimi Streaming Audio Codec
Mimi is a neural audio codec that compresses speech into a tiny stream of discrete tokens in real time, so AI models can listen and speak with very low…
Audio AIListen Attend and Spell
Listen, Attend and Spell (LAS) is a landmark 2015 neural network that transcribes speech directly into characters, with no hand-built pronunciation…
Audio AISpecAugment for Speech Recognition
SpecAugment is a simple but powerful data augmentation method that masks and warps the spectrogram of speech to make recognition models more robust.
Audio AIMusic Auto-Tagging
Music auto-tagging uses machine learning to listen to a song and automatically attach descriptive labels like genre, mood, instruments, and tempo.
Audio AIMusical Timbre Transfer
Timbre transfer reshapes the 'tone color' of audio so one instrument sounds like another, turning a hummed melody into a violin or a trumpet line…
Audio AIAcoustic Scene Classification
Acoustic scene classification (ASC) trains machines to recognize the environment a recording was made in, a busy street, a quiet park, a train, a cafe…
Audio AINVIDIA Riva and NeMo Speech
NVIDIA Riva is a GPU-accelerated SDK for production speech AI (ASR, TTS, and translation), while NeMo is the open-source toolkit for training and fine-tuning…
Audio AIDeepSpeech Architecture
DeepSpeech is an end-to-end speech recognition model introduced by Baidu in 2014 that maps raw audio features directly to text using a recurrent neural…
Audio AIX-Vector Speaker Embeddings
X-vectors are fixed-length numerical fingerprints of a speaker's voice produced by a neural network, used to tell who is speaking regardless of what they say.
Audio AIGlow-TTS Monotonic Alignment
Glow-TTS is a text-to-speech model that learns to align text to speech on its own using a clever search trick, removing the need for a separate aligner.
Audio AIParallel WaveGAN Vocoder
Parallel WaveGAN is a fast neural vocoder that turns a mel-spectrogram into a raw audio waveform using a small GAN, generating all samples at once.
Audio AIWaveGlow Flow-Based Vocoder
WaveGlow is a flow-based neural vocoder from NVIDIA that synthesizes speech waveforms from mel-spectrograms in a single pass without autoregression.
Finished reading? Prove it.
Check what you learned with topic quizzes, then explore our structured courses and current certification requirements. Core guides remain free to read.