Loading...
Loading...
Audar ASR V1: Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Audar ASR V1. This is an automatic list. We have not written a researched verdict for Audar ASR V1 yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
AI Dictation App - Open Source and Local-first Type 3x faster, no keyboard needed.
Amical is an open source AI dictation app that turns speech into formatted text in whatever application is in focus. Rather than producing a raw transcript, it reads the context of the app being used and shapes the output to suit it, so a dictated passage becomes a professional email in Gmail, a casual post on social m...
Atomic Agent is a local-first AI agent.
Atomic Agent is an open source, local first AI operator that runs on the user's own machine and drives real tools: the browser, the file system, the shell and git. It runs a local model through llama.cpp, so there is no cloud account, no API key and no token bill, and every session is stored on the user's own disk. It ...
System audio capture + multi-provider ASR + local-first AI review workspace.
DeLive is a free, open source desktop transcription workspace for Windows, macOS and Linux. It captures system audio directly, so meetings, lectures and podcasts can be transcribed without a microphone, and it also transcribes uploaded audio and video files. Transcripts are then reviewed with AI for correction, summari...
JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME.
JANG is an open source quantization method for running larger AI models on Apple Silicon Macs. It is built around the MLX framework and shrinks model files so that bigger, more capable models fit in the memory of a laptop or desktop Mac while keeping output quality higher than uniform quantization at the same size. St...
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Nobodywho is an inference engine that runs AI models directly on devices and on company servers, with no calls to an external model provider. It is built and maintained in Copenhagen and released under the EUPL 1.2, the European Union's open source licence, with development done in public on GitHub. The engine ships a...
Fine-tune LLMs from one YAML.
Soup is an open source command line tool for post training large language models on local hardware, built by MePlay, Inc. and released under the Apache 2.0 license. It installs with pip and covers the workflow from data checks to shipping a model in a single CLI. Its central technique is layer streaming. Instead of lo...