Primate Labs released Geekbench 7 today, featuring overhauled CPU and GPU performance tests that emphasize machine learning, content creation, and real-world tasks such as face tracking, image upscali…
Pete Warden, an AI researcher and instructor, demonstrates how open-source AI running locally on a Raspberry Pi can solve practical setup problems, such as configuring wifi by voice, addressing the fr…
Interfaze, a research lab, released diffusion-gemma-asr, the first open-source diffusion ASR audio model that is 15x faster than OpenAI's Whisper. The model achieves a 6.6% word error rate on Librispe…
VidDojo, a new AI-powered platform, turns any YouTube video into an interactive course by inserting questions inside the player and rewinding to the exact spot on wrong answers. The tool automatically…
A developer built a self-learning video editing agent using Claude Skills that can automatically edit a 30-minute video in 10 minutes. The agent separates five core editing tasks into independent Skil…
DictaFlow's development testing shows Parakeet offers near-instant local dictation on iPhone and Mac with a 483 MB download footprint, while Whisper provides better vocabulary, accent handling, and la…
OfflineTTS, a free browser-based text-to-speech and speech-to-text toolkit that runs locally, has launched with support for four TTS engines, 99 STT languages, and workflows for subtitle generation, v…
Christopher 'CJ' Pais, creator of the desktop dictation tool Handy, released transcribe.cpp on June 30 as an MIT-licensed C/C++ library that unifies local speech-to-text inference across macOS, Window…
EnviousWispr, a free open-source AI dictation app for macOS, runs entirely on-device using Whisper and Parakeet speech-to-text models on Apple Silicon, with no cloud, account, or subscription required…
A developer built Hands Free Notes, an Android app that uses OpenAI's Whisper model for offline speech-to-text transcription. The app processes voice notes entirely on-device, requiring no account, se…
Timeline Studio, a local-first AI video editor that runs in the browser, combines a CapCut-style multi-track timeline with browser-side AI voiceovers, automatic captions, vision tools, talking-avatar …
A developer built a 100% local personal assistant using Ollama, LangChain, and voice, running entirely on a laptop GPU with no API calls. The project exposed key differences between cloud-based 70B+ m…
Velora, an open-source macOS dictation tool that runs entirely on-device using Apple Silicon and MLX, has been released under an MIT license. The tool uses Whisper for speech-to-text and a local LLM f…
NexSub, a fully offline AI video subtitle translator using local Whisper models, launches as the world's first tool to provide real-time multilingual subtitles without internet or cloud costs. It supp…
OpenAI Whisper is the most capable open-source speech-to-text engine available in 2026, supporting 99+ languages with near-human accuracy, according to OpenAI. The model, trained on 680,000 hours of m…
A new study finds that denoising audio with SAM-Audio preprocessing paradoxically worsens zero-shot automatic speech recognition (ASR) performance. Researchers tested five OpenAI Whisper variants on n…
VoiceBox, an open-source voice-to-text tool built with Wails, Cloudflare Workers, and Whisper, transcribes speech and formats output via an LLM when a user presses a hotkey, with auto-paste on macOS. …
Google researchers introduced DiffusionGemma, a 26-billion parameter mixture-of-experts speech recognition model that uses discrete diffusion to refine whole transcripts in parallel, achieving a 6.6% …
A developer built a private, local voice assistant using Python and OpenAI's Whisper model, combining speech-to-text with offline text-to-speech to avoid cloud dependencies. The assistant runs entirel…
Spet, a free no-signup transcription service, offers strong accuracy on non-English audio by running OpenAI's Whisper large-v3 model on a GPU. The tool supports 90+ languages, deletes audio immediatel…