Dionext software development notes

AI Use Cases, Software Based on AI

Using for Programming

See Using for Programming

Using for Media (Arts, Images, Video, Design, etc.)

See Using for Media (Arts, Images, Video, Design, etc.)

Using for Texts, Search, Summarization

https://www.youtube.com/watch?v=Gn64NNr3bqU&t=37s AI Summarize HUGE Documents Locally! (Langchain + Ollama + Python)

https://www.youtube.com/watch?v=9KKnNh89AGU&t=98s Build a LOCAL AI Web Search Assistant with Ollama

Video Summarizer

https://videosummarize.ai/

https://play.google.com/store/apps/details?id=com.emote.youtube_summarizer&hl=en

VideoSummarizer currently works best with YouTube videos that have subtitles in them. But we're working hard on making it work with all kinds of videos.

Using for Language Translations and Learning

https://www.youtube.com/watch?v=J_Dm5UqRNDs Мария Мичурина | Case study как быстро и дешево переводить новости для требовательного заказчика

https://smalltalk2.me/ Boost Your Confidence in Spoken English AI-powered simulator to self-practice the IELTS speaking test, job interview and everyday conversational English

Using for Speech-to-Text and Text-to-Speech

Google Docs Voice Input https://support.google.com/docs/answer/4492226?hl=en

Microsoft SwiftKey https://www.microsoft.com/en-us/swiftkey

https://www.youtube.com/watch?v=ehwClU5Ey_k ChatGPT's SECRET Text To Speech is FREE & UNLIMITED

https://www.youtube.com/watch?v=_diVy9VdT5s{#id47} How to Build Free Voice AI Agents With LiveKit - Beginner's Tutorial

@my_voice_messages_bot - I convert audio to text using AI. You can send me a voice message, a round video, a YouTube link, or a meeting recording. I can also:

https://vobox.io/ Natural Text to Speech & AI Voice Generator Professional voiceovers for your videos and presentations are made possible by VOBOX's extensive range of natural-sounding AI voices in 125+ languages.

https://www.youtube.com/watch?v=yFO1PJ0NEFk Нейросеть превращает аудио в текст. Бесплатно!

https://sonix.ai/ Automated transcription in 53+ languages. Fast, accurate, and affordable. https://www.youtube.com/watch?v=VGcLFZ2zwp8

https://vapi.ai/ Voice AI for developers Vapi lets developers build, test and deploy voice agents in minutes rather than months.

https://elevenlabs.io/ ElevenLabs: Free Text to Speech & AI Voice Generator ElevenLabs https://elevenlabs.io · Перевести эту страницу Create the most realistic speech with our AI audio tools in 1000s of voices and 32 languages. Easy to use APIs and SDKs.

https://deepgram.com/ The Voice AI platform for developers Deepgram's voice AI platform provides APIs for speech-to-text, text-to-speech, and full speech-to-speech voice agents. Over 200,000+ developers use Deepgram to build voice AI products and features. (Price ~ $0.0048/min)

https://www.rask.ai/ Intelligent video localization at scale - (Voice translation to another voice) ($50 Billed annually / per month 25 minutes included)

https://ramblefix.com/ Hit record and start rambling, RambleFix will transcribe, clean up and rewrite what it hears. Say goodbye to manual note-taking. You can upload files too - perfect for meetings, lectures & interviews. ($5/month 20 minute recordings )

https://speechflow.io/ Accurate speech-to-text API for all languages beyond just English Our speech-to-text ASR API transcribes 14 languages with increased accuracy 20% higher than other market players ($0.0002 per second - 0.012/min)

https://www.amberscript.com/en/ Transform your audio and video to text and subtitles Our cutting-edge generative AI, paired with top-tier language professionals, collaboratively deliver highly accurate solutions tailored to your business needs. (from: $20 - 1 hour of audio or video uploaded)

https://www.rev.ai/ Rev AI (from $0.20 / hour)

https://www.descript.com/ ($12 per person / month - 10 transcription hours / month )

https://www.edenai.co/ (proxy) The full-stack AI platform for developers to efficiently create, test, and deploy AI: unified access to the best AI models combined with a powerful workflow builder and monitoring tools. Unified Access to Top Speech APIs at Competitive Prices With Eden AI, enjoy a unified API that connects you to the best Speech APIs available. Benefit from competitive pricing-pay only what model suppliers charge-without the hassle of multiple accounts. Centralized billing makes management a breeze! https://app.edenai.run/models?ajs_aid=8f4a8f87-fa26-4380-b7f3-32b26b902a9d Compare pricing per 1 minute

https://github.com/fishaudio/fish-speech text-to-speech and voice cloning https://www.youtube.com/watch?v=qwNHF4bmn48 (ru)

https://silero.ai/ (ru)

Whisper AI

Whisper ASR Webservice

https://ahmetoner.com/whisper-asr-webservice/endpoints/

How to Install & Use Whisper AI Voice to Text https://www.youtube.com/watch?v=ABFqbY_rmEk

https://hub.docker.com/r/onerahmet/openai-whisper-asr-webservice

Whisper ASR Webservice https://ahmetoner.com/whisper-asr-webservice/run/

docker pull onerahmet/openai-whisper-asr-webservice:latest

docker run -d -p 9000:9000 -e ASR_MODEL=base -e ASR_ENGINE=openai_whisper onerahmet/openai-whisper-asr-webservice:latest

(docker pull onerahmet/openai-whisper-asr-webservice:v1.8.2)

http://[host]:9000/docs

2b9aedf1fd80 keen_wiles 0.29% 801.7MiB / 3.82GiB 20.49%

WhisperX {#whisperx}

WhisperX stands out as the most versatile and feature-rich Whisper variation. Here's why it's our top pick:

  1. Fast automatic speaker recognition: WhisperX adds word-level timestamps and speaker diarization, making it ideal for multi-speaker transcriptions.
  2. Speed: It uses Faster-Whisper under the hood, providing a 4x speed increase compared to the original Whisper.
  3. Language support: While not universal, WhisperX supports a wide range of languages including English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Mandarin Chinese, and Japanese.

https://github.com/m-bain/whisperX This repository provides fast automatic speech recognition (70x realtime with large-v2) with word-level timestamps and speaker diarization.

SuperWhisper

https://superwhisper.com/ AI powered voice to text for macOS (>= 13).

https://www.youtube.com/watch?v=loIvdOpqn5Q Top AI Dictation Tools: MacWhisper, Wispr Flow, Superwhisper, and a Local Alternative with Aiko

https://www.youtube.com/watch?v=lCh4FDInVtY (ru) Superwhisper DEMO. AI Mindset [lab]

Other Ports

https://github.com/Const-me/Whisper This project is a Windows port of the whisper.cpp implementation. + models https://huggingface.co/ggerganov/whisper.cpp

https://www.youtube.com/watch?v=rLeMPakTwxE Faster Whisper? Whisper X? Insanely Fast Whisper? Piotr recommends Whisper2ST + ctranslate2

Using for Internet Content Generation

https://websim.ai/ sites constructor https://www.youtube.com/watch?v=ydWT4nqgJcY

https://podcastle.ai/ Many AI tools for creating podcasts. For example: Unleash the power of AI to transform your low-quality audio recordings into studio-level sound with our AI Audio Enhancer Magic Dust.

https://gerwin.io/ Grewin AI is a Russian text creation service. It can create posts for various social networks, articles, headlines and much more - the site offers dozens of templates for generation. The service does not work by subscription - you pay for the number of characters.

https://rytr.me/ Rytr's AI generates original and compelling content that sounds like you, not a robot.

https://www.youtube.com/watch?v=KS4jWCm0VfI Нейросети для создания контента: БЕСПЛАТНЫЕ И СУПЕР УДОБНЫЕ

https://www.youtube.com/watch?v=Xx86hL0P83Q AI БЛОГЕР от А до Я: РУКОВОДСТВО ПО СОЗДАНИЮ И МОНЕТИЗАЦИИ

https://app.gravitywrite.com/ https://app.gravitywrite.com/pricing Free Get - 1,000 Words/mo $19/Month - Get 75,000 Words/mo https://www.youtube.com/watch?v=eaivzIPKhqg How To Create Blog Using AI | Complete Blogging Tutorial

It is recommended that Claude is better suited for generating simple articles, and Gemini is better suited for generating complex projects based on prompts. https://www.rush-agency.ru/blog/kak-pisat-kachestvennye-stati-ispolzuya-ii/ (ru)

Using for Science

https://www.youtube.com/watch?v=CMizH-0uJRw AI mindset [knowledge]: Итоги 8 недель лаборатории управления знаниям с Obsidian и AI рекомендуют How to Take Smart Notes (Sönke Ahrens)

https://www.youtube.com/watch?v=T2aYngze9Ko Промпты для Ученых в ChatGPT: Как Использовать ИИ для Научных Исследований?

https://www.youtube.com/watch?v=sUJMAx_dfR4 Умная Таблица = 100 Задач за 5 секунд! (работа с excel ТАБИЫЦАМИ)

https://www.youtube.com/watch?v=K0HquGPI55A Написание научных работ с помощью нейросетей: Повышаем качество и эффективность | Наталья Киреева

Lazy AI (lazy.so)

(есть с похожим названием но другой софт https://www.getlazy.ai )

идея чем-то сходная с Zotero

https://lazy.so/

https://www.producthunt.com/products/lazy

What is Lazy? Context switching is poison for productivity. When you get that brilliant idea or see something inspiring, you should be able to take smart notes without switching app or tabs. That's Lazy. One shortcut to capture anywhere. Sign up to our waitlist at lazy.so!

For Zotero

https://www.youtube.com/watch?v=zEYp0BJL7MU How I research and write in Obsidian (and Zotero)

https://www.youtube.com/watch?v=b2BSZfOtD_w How to connect a LLM to Zotero for a private, local research assistant -- fast, no code

{#id49}A.R.I.A plugin for Zotero https://www.youtube.com/watch?v=gA3o2MlnPBQ How to use Zotero's full potential [The AI Revolution in Zotero] https://github.com/lifan0127/ai-research-assistant

https://www.youtube.com/watch?v=hRCiuycpAIU How to Connect Zotero and Obsidian for the Ultimate PhD Workflow

Using for Everyday Life

https://www.ray-ban.com (device) Ready for the next generation of smart glasses? The Ray-Ban Meta collection combines the latest in wearable tech with authentic Ray-Ban design, to keep you connected wherever you go. The Ray-Ban Meta smart glasses take all the features of Ray-Ban Stories and elevate them to meet what users really want.

https://www.limitless.ai/ (device) Go beyond your mind's limitations Personalized AI powered by what you've seen, said, and heard.

VAPI ($10 free credits): https://vapi.ai/?via=sanava Retell AI (60 free call mins): https://dashboard.retellai.com//?ref=... LiveKit: https://livekit.io/ FREE RESOURCES : https://sanava-ai.com/resource-hub/

https://github.com/ilyhalight/voice-over-translation About Небольшое расширение, которое добавляет закадровый перевод видео из YaBrowser в другие браузеры

https://www.youtube.com/watch?v=vnunc-wYzec 5 лучших ИИ РАСШИРЕНИЙ для БРАУЗЕРА, которые УСКОРЯЮТ работу

Using for Tourism

https://www.youtube.com/watch?v=httlaqQ2cgY Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles - ArXiv:2

Earth Copilot https://blogs.microsoft.com/blog/2024/11/14/from-questions-to-discoveries-nasas-new-earth-copilot-brings-microsoft-ai-capabilities-to-democratize-access-to-complex-data/

AI Workflow and AI Agents

https://github.com/langgenius/dify Dify is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

https://agpt.co/ Empower your digital tasks with AutoGPT Welcome to AutoGPT, where AI amplifies human potential. Our platform empowers you to create intelligent assistants that streamline your digital workflow, enabling you to dedicate more time to innovative and impactful pursuits.

http://babyagi.org/ This newest BabyAGI is an experimental framework for a self-building autonomous agent. Earlier efforts to expand BabyAGI have made it clear that the optimal way to build a general autonomous agent is to build the simplest thing that can build itself.

https://n8n.io/ Secure, AI-native workflow automation (Price from $20 month) https://www.youtube.com/watch?v=jdyO1l8Hokk Smart AI Blog Writing System: Fully Automated Content with n8n

https://www.make.com/ Automation at scale - on one visual platform Automate workflows, integrate apps, and power innovation - on Make's visually intuitive no-code development platform.

https://www.youtube.com/watch?v=L4uST6vOTac Make vs n8n-The Wrong Choice Will Cost You ( https://www.youtube.com/watch?v=AsstdtiX8XU (ru))

Other Uses

https://www.youtube.com/watch?v=slfC9um1qdk RAG. Делаем вопросно-ответную систему с поиском по базе видеороликов https://github.com/trashchenkov/gigachat_tutorials/blob/main/RAG_по_видеороликам.ipynb все его репозитории https://github.com/trashchenkov/gigachat_tutorials есть пример и для статей

https://secondnature.ai/ Customer-facing teams sell better after AI training with us! Use AI life-like sales training to role play any conversation. Boost sales, enhance training effectiveness, and increase productivity.

https://customgpt.ai/ Instant Answers From Your Information No code, no training, just results: The #1 no-code platform for creating custom AI agents for your business.

Catalogs and Reviews

{#id28}https://ailibri.com/ (ru) catalog of neural networks for all kinds of tasks! Here you will find an extensive list of neural networks suitable for various areas of application. More than 2000 neural networks are collected in our catalog and distributed among more than 70 AI categories to meet the most diverse needs.

https://aipure.ai/ AIPURE helps you find the best AI tools of 2024 easily!