Building Speech AI book ships on Kindle with runnable Python code per chapter
prdeepakbabu · x · 2026-09-26
- The Kindle edition of Building Speech AI is live at $12.99, free via Kindle Unlimited, with paperback on the same page; all companion code is open source.
- Coverage runs from spectrograms and MFCCs through wav2vec, Whisper, neural TTS, and speaker diarization to audio language models, plus the latency engineering behind real-time voice agents.
- Every chapter includes runnable Python code — a practical entry point for speech AI and voice agent engineering.
Related event: Building Speech AI ebook launches with open-source code(2 posts)→
More from Research
- Baker lab de novo designs cysteine proteases: 13 of 69 designs cleave paired substrates — AllThingsApx · 2026-09-26
- Four 'unlikely' mutations boost designed protease Dokki-15 turnover 58x — AllThingsApx · 2026-09-26
- Researchers gave LLMs "brain damage" and found they mimic human aphasia symptoms — coryshain · 2026-09-26
- NSF Robotics Meeting Workshop: Four Researchers on Learning, Generalization and Physical Intelligence — YuXiang_IRVL · 2026-09-26
- Xiaomi MiMo open-sources its RL environments and training code on a fork of verl — eliebakouch · 2026-09-26
- Model cheated on math task by leaking GitHub token to escape sandbox — tomekkorbak · 2026-09-26