Natural Language Processing news and analysis on Web Pulse: 5421 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
A developer built Student Expense AI, a tool that lets a college friend log expenses by typing natural-language entries such as "I spent ₹180 on lunch today," which the system then categorizes and tracks against budgets.…
A developer built Placement Pronunciation Coach, a locally-run AI speech evaluation dashboard that uses Whisper word timestamps and per-word confidence probabilities below a 0.75 threshold to flag unclear words, then app…
A developer built J.O.H.A.N (Just One Hilarious Answer Now), a locally run AI comeback generator that helps a friend respond to a bully with witty one-liners in English and Manglish. The system pairs Google's open-weight…
A developer launched Bearbits, a browser-based AI meeting copilot that provides real-time transcription, live translation across mid-meeting language switches, and web-search-grounded response suggestions, built using So…
A developer built Unsaid, a 100% local-first AI reflection room for a friend with severe ADHD and racing thoughts, keeping all data on-device. The open-source MIT-licensed app pairs Google's Gemma 3 4B running locally vi…
Jeffy Playground launched a catalog of 16 pretrained text classifiers that developers can install via `pip install jeffy-classify` and run on CPU without a GPU or API keys. The demos include SMS spam detection at 99.1% a…
Moondream released Parakeet Redux, a speech-to-text model that compresses NVIDIA's 1.2 GB Parakeet 0.6B v3 to 178 MB via ternary quantization of the encoder weights, cutting Word Error Rate on seven English benchmarks on…
Anthropic's Claude Opus 5.5, released September 22, 2026, shows a 19% lower word-distribution divergence from human writing than Opus 5, while OpenAI's GPT-6 Astra's divergence is 8% higher than GPT-5.6 Sol's, according …
A developer built Udhaar Khata, a voice-powered digital credit ledger for their father's neighbourhood shop in India, running entirely on local open-weights models. The app uses OpenAI's Whisper for Hindi and Hinglish sp…
A developer released SCM 0.2.4, a local-first AI search app for macOS that indexes every photo and every frame of video in watched folders using on-device vision models, OCR via Tesseract, and dialogue search via Whisper…
A developer built voice-recipe-book, an open-source pipeline that transcribes voice memos with faster-whisper and structures them into Markdown recipe cards using Qwen2.5-3B-Instruct, all running locally on CPU with no c…
A developer built Heirloom AI, a project that uses open-weight Gemma AI and ElevenLabs voice synthesis to convert an elderly grandfather's rambling voice memos into structured, standardized recipes stored in an interacti…
A developer published a guide to voice AI security and privacy, cataloging common attack vectors including voice-based phishing (vishing), replay attacks, unencrypted audio storage, and model inversion against TTS system…
A cost-versus-quality comparison of voice AI text-to-speech platforms finds ElevenLabs delivers higher-rated voice quality at roughly a third of the per-character price of top-tier neural voices from Google Cloud, Amazon…
A developer built tl;dr, a local LLM tool that reads exported WhatsApp college group chats and extracts deadlines, events and plan changes into a markdown summary and importable calendar file. The pipeline runs Gemma 4 (…
Donal Muolhoi trained a Hmar language model, HmarBERT, by fine-tuning from a Mizo model after a university professor suggested the approach, and published it on Hugging Face under the Hmar Heritage Foundation. Muolhoi, w…
A developer built RapidOS, an open-source WhatsApp claims assistant for insurers in the Democratic Republic of Congo, released under AGPL-3.0 and deployable with a single `docker compose up`. The system connects each ins…
A developer built LectureBuddy, an open-source, browser-based study tool that converts PDF slide decks, Word documents, and smartphone photos of handwritten notes into simplified lecture summaries, glossaries, flashcards…
A developer built Gev, a browser extension that reads Gmail messages and automatically applies labels such as Receipts, Personal, Updates, and Newsletters. The extension runs the Laya model via Transformers.js with the O…
A developer has published a practical guide to choosing audio formats and quality settings for voice AI pipelines, comparing MP3, AAC, WAV, FLAC, OGG Vorbis and Opus across bitrate, sample rate and use case. The writeup …