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 unc…
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 H…
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 dialogu…
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 loca…
A new short-video channel produced twelve AI-generated clay-styled films about famous frauds in five days for $184 in fal.ai image and video costs, using the coding agents Claude Code and Codex to run…
A developer built Investment Memory, a personal investment decision journal for his father that records the reasoning behind each investment rather than generating buy or sell recommendations. The app…
Cactus Compute released Whistle, a 16.9 MB on-device speech recognition model that runs on CPU with no dependencies and loads into the same C++ engine as Needle. Whistle handles transcription in seven…
A software developer intern at Plumo AI built roughly 80% of the company's AI video generation platform during a summer internship, including the Flutter frontend, most of the NestJS backend, and a mu…
A developer has published a step-by-step guide for building an AI-powered voice call application that combines Twilio's telephony webhooks with ElevenLabs' text-to-speech API and OpenAI's GPT-4o-mini …
A developer guide argues that teams building AI meeting-notes features should buy hosted transcription from vendors like Deepgram and AssemblyAI and build only the summarization, decision-extraction a…
Two memory-safety vulnerabilities in CTranslate2, the inference engine behind Whisper and OpenNMT, were disclosed on September 29, 2026, and fixed in version 4.8.1. CVE-2026-102566 (CVSS 7.8) is a hea…
YuliusBox launched as a free browser-based suite of 26 tools that process files locally on the user's device using WebAssembly, the Canvas API, and on-device AI models such as Whisper, with no uploads…
A developer released Off Grid AI Mobile, an Android app that runs Whisper speech recognition entirely on-device, letting users transcribe Hindi, Spanish, French and other supported languages without a…
A developer published a step-by-step guide for building a voice-enabled chatbot that chains OpenAI's GPT-4 and Whisper with ElevenLabs' text-to-speech API. The Python script records microphone audio, …
Google released Gemini 3.5 Transcribe on August 26, 2026, a two-model transcription line that Google says delivers a 70% improvement in time-to-final-transcription over Chirp 3, with a 4.0% word error…
A solo developer building Katto, an AI video clipper, discovered that a language-model-based proper-noun correction pass was silently renaming an unknown model called "Jev" to the real model "Jamba" a…
Marimo's notebook sandboxes now support Pixi, letting standalone notebooks record Conda and PyPI requirements alongside their code, the marimo team announced. The integration, built with the Pixi team…
A developer built GramSetu AI, a conversational civic assistant for rural Indian micro-entrepreneurs that handles Telugu voice notes and text queries across sessions spanning weeks. The team replaced …
A new arXiv paper (2609.30469v1) reports that an external LLM-as-a-judge filtering paradigm significantly reduces word error rate in pseudo-labeled training sets for noisy Broadcast Police Communicati…
Researchers introduced asymmetric classifier-free guidance (CFG) for target-speaker automatic speech recognition using Whisper, reporting relative word error rate reductions of up to 21.8% over the co…