AI catalog — tools for text, images, video, and code
All categories

Speech-To-Text

Freemium
Upvote 0
NoteOwl is an AI meeting notes application designed for Apple silicon Macs. It operates privately, recording, transcribing, and summarizing meetings directly on the device without the need for a bot to join the call. The app automatically identifies speakers, extracts action items, and tracks commitments made by each participant. Users can search through all past meetings using plain English queries and receive answers that are linked to specific moments in the recordings. NoteOwl functions fully offline after an initial model download and is available as a one-time purchase, without any subscription fees.
Freemium
Upvote 0
Jarq is a Mac application designed to boost productivity. It allows users to translate, shorten, correct, or rewrite text directly within any application, eliminating the need to switch tabs or perform copy and paste operations. The app includes an inline dot trigger that applies AI-driven text actions precisely at the cursor's location. Jarq also offers voice dictation functionality accessible via a hotkey. It converts spoken words into clear, properly punctuated text across all applications. The voice data remains on the device, ensuring privacy, while the text processed through the cloud is not stored or utilized for training purposes. Jarq is available either for free with daily usage limits or through a Pro plan, accessible via subscription or a one-time purchase.
Freemium
Upvote 0
Hilite is a comprehensive AI-driven podcast platform designed for creating, editing, refining, and publishing audio content. It offers features like converting audio to text for easier editing, eliminating background noise, and quickly balancing audio levels. Users can create AI-generated show notes, analyze listener data, and publish episodes to platforms like Spotify, Apple Podcasts, and others with a single click. Hilite caters to independent podcasters, educators, writers, wellness professionals, and other creators aiming to minimize production time.
Freemium
Upvote 0
Streva is a macOS application that uses AI for translation and dictation. It seamlessly integrates into any app, eliminating the need to copy and paste between different tools. This tool can convert speech to text at a speed of up to 220 words per minute. It understands the intent and tone, producing natural and contextually appropriate writing. Streva supports over 100 languages and adjusts its formatting according to the application being used. There is a free plan that allows for 2,000 words per week, and a paid Pro plan that offers unlimited dictation.
Paid
Upvote 0
Viora is a voice AI assistant for macOS that allows you to hold a shortcut, speak naturally, and have AI input into any app, rewrite or edit selected text, answer context-aware questions, or execute small tasks without changing windows. It understands your intent (such as dictating, editing, asking, or doing) and keeps an editable memory of your preferences and threads to maintain context. Use it to accelerate writing, enhance tone and clarity, reduce copy-pasting and app switching, and delegate routine text tasks while retaining control over what Viora remembers and how your data is stored.
GitHub
Upvote 0
Whisper is a publicly available system for automatic speech recognition, developed using 680,000 hours of multilingual and multi-task supervised data sourced from the internet. It is crafted to effectively handle various accents, background noise, and technical jargon, and it can convert and translate spoken language in numerous tongues into English. This straightforward end-to-end method is executed as an encoder-decoder Transformer. Additionally, it can identify languages and provide timestamps at the phrase level. It aims to offer ease of use and high precision, enabling developers to integrate voice interfaces into more applications.