12ui
12ui (https://12ui.com/) generates web interfaces (HTML/CSS) from a drawing or a diagram with shapes or texts made directly in the...
Arky
Arky (https://arky.so/) is an infinite whiteboard-style visual workspace combined with a chatbot to structure a project or ideas. Elements can...
Reka
Reka (https://reka.ai/ and models: https://huggingface.co/RekaAI) offers several multimodal models for image and video analysis, text and voice.Two first versions were...
Podcasty
Podcasty (https://podcasty.fm/) generates podcast episodes from online articles. Two entries possible: via an RSS feed for automation or article by...
ChatGPT images 2.0
ChatGPT Images 2.0 (https://chatgpt.com/) is the latest image generation model from ChatGPT. Fine text support, generation of visuals, infographics and...
NBot
NBot (https://nbot.ai/) generates an automated monitoring from an instruction and the answer to questions that allow it to be refined....
Gemini 3.1 TTS Preview
Gemini 3.1 TTS Preview (demo on Google Ai studio https://aistudio.google.com/generate-speech?model=gemini-3.1-flash-tts-preview) is Google’s latest text-to-voice model. Two modes of presentation: text...
Dailyscope
Every day, Dailyscope (https://www.dailyscope.ai) analyses international press sources (not French sources) to bring out the main themes and allow comparison...
Smol LM 3
Smol LM 3 (documentation: https://huggingface.co/HuggingFaceTB/SmolLM3-3B and demonstration: https://huggingface.co/spaces/HuggingFaceTB/SmolLM3-3B-WebGPU) is a very lightweight language model (3 B parameters), produced by Huggingface....
Google Flow Music
Flow Music (https://www.flowmusic.app) is Google’s latest generative AI app after the acquisition of Producer (seen here now archived), which generates...
Rosebud
Rosebud (https://rosebud.ai/) generates games from instructions. After iterations with a chatbot, Rosebud generates the graphics and then the game. Iterations...
Holotab
Holotab (https://chromewebstore.google.com/detail/holotab/hlaoiikljjgcjdhkakedfngifaopbcop) is a Chrome extension launched by HCompany (a French company already seen here with Runner H) and which...
Pascal Editor
Pascal Editor (application: https://editor.pascal.app/ and documentation: https://github.com/pascalorg/editor) generates, from instructions in a chatbot, 2D and 3D architectural plans with realistic...
LearnClash
LearnClash (https://learnclash.com) offers quizzes to be solved individually or in duel, or generated from a given topic. A chatbot allows...
Maskerade
Maskerade (https://maskerade.ai/) generates reports in response to an instruction via the actions of multiple personas. After analyzing the instruction, Maskerade...
Wiki Timeline
Wiki Timeline (https://wiki-timeline.com) generates timelines from one or more Wikipedia articles (added via search or url). 20 languages available.Configurable formatting,...
Muse Spark
Muse Spark (description: https://ai.meta.com/blog/introducing-muse-spark-msl/) is Meta’s proprietary model available in apps and in meta.ai. Multimodal and with reasoning and web...
World Monitor
World Monitor (https://www.worldmonitor.app/ and documentation: https://www.worldmonitor.app/docs/documentation, github: https://github.com/koala73/worldmonitor) is a real-time dashboard that brings together global geopolitical and economic information...
Blueprint
Blueprint (https://www.blueprint.am/) generates detailed prototypes from an instruction and a chatbot. The generation consists of a view of the object...
Google Vids – Veo 3.1
Google Vids (https://docs.google.com/videos) integrates Veo 3.1, the latest version of Google’s video generator, Gemini Music (Lyria 3) for auto-generated soundtracks,...
Adam
Adam (https://adam.new/ and documentation: https://github.com/Adam-CAD/CADAM) is a model that, coupled with a language model, transforms a natural language query into...
Voice Generator
Voice Generator (https://voice-generator.com/) transforms texts into voices from written or pasted text, pdf or epub. 12 languages and 70 voices...
Gemma 4
Gemma 4 (description: https://huggingface.co/blog/gemma4) is the latest open-source model from Google.It is available on Hugging Face, in the Google AI...
Zawa
Zawa (formerly X-design – https://zawa.ai/) is a chatbot combined with a whiteboard specialized in the generation of visual content, image...
Scholar Labs
Scholar Labs (https://scholar.google.fr/) is an experimental natural language search engine integrated with Google Scholar, accessible from the menu bar. Based...
Pixpark
Pixpark (https://pixpark.ai/) generates images from a reference statement or image. Multiple formats and resolutions available (up to 4K). Note: for...
Seedance 2
Seedance 2 (available in Capcut and in Dreamina) is the latest version of ByteDance’s video generation model. On CapCut, two...
Molmo web
Molmo Web (Documentation: https://allenai.org/blog/molmoweb and demonstration: https://molmoweb.allen.ai/) is a web agent that automates an internet search ordered by an instruction...
Coherent transcribed
Cohere Transcribe (documentation: https://huggingface.co/CohereLabs/cohere-transcribe-03-2026 and demonstration: https://huggingface.co/spaces/CohereLabs/cohere-transcribe-03-2026) transcribes recorded or imported audios. 12 languages available including French.Very faithful and fast...
BookletAI
BookletAI (https://bookletai.org) generates “booklets” in the form of HTML pages that turn or pdfs that can be shared and presented...
Omma
Omma (https://omma.build/) generates applications and web pages from instructions with a specialization in 3D models. Great respect and understanding of...
Thaura
Thaura (https://thaura.ai/), “revolution” in Arabic, is an ethical, frugal, committed… and very complete chatbot. Developed by two Syrian developers and...
Public ai
Public Ai (Chatbot: https://chat.publicai.co, project website: https://publicai.co/ and documentation: https://github.com/forpublicai) is an open-source chatbot based on the Apertus language model...
Video notes
Video Notes (https://www.video-notes.co/) offers YouTube video analysis with transcript, detailed summary, analysis, chatbot, and notes. Export Markdown & TXT. Many...
Tosea
Tosea (https://tosea.ai/) generates presentations from a pdf document (orientation to scientific articles and academic documents) and an integrated chatbot. After...
Thinkingline
Thinkingline (https://www.thinkingline.com/) generates educational videos and vector images from an instruction in animated sketchnote mode with oral presentation. 3 styles...
Commabot
Commabot (https://commabot.com/) parses csv files from instructions. The answers provided are aggregated in new csv files integrated into the conversation...
Make it
Make it (https://make-it.ai) transforms ideas for technical objects to make yourself into a documented project, from the list of materials...
Wacka
Wacka (https://whacka.app) generates online mobile applications from an instruction and a chatbot. No export and model not specified. Share by...
Cartesia Sonic
Cartesia Sonic (https://cartesia.ai/sonic) is a “Text-to-Voice” application deployed with two versions: a text generation version and a searchable audio chatbot...
Clico
Clico (https://tryclico.com/) is a browser extension (Chrome, Edge, Brave, Arc, and all Chromium-based browsers) that integrates the features of a...
Creatus Music
Crztus Music (https://music.creatus.ai) generates music tracks from a genre with an instruction or imported lyrics. The generation of instrumental pieces...
Knowlify
Knowlify (https://www.knowlify.com – choose “Platform”) manages explainer videos from an instruction and a chosen voice. The editable script is generated...
Gistilo
Gistilo (https://gistilo.com) summarizes videos YouTube. Two modes offered: the 7 highlights and detailed summary. For the French videos, English version...
Creen
Creen (https://www.creen.ai) generates images and videos from an instruction or images. Three models for image generation (Creen / seedream /...
Medo
Medo (https://medo.dev) builds applications from a statementTwo build modes, “fast” and “Deep Build”, extensions and designs are offered. Medo starts...
Intangible
Intangible (https://studio.intangible.ai) generates 3D scenes from an image. Once the scene is generated, the user takes screenshots with the dedicated...
Cloudfare Build
Cloudfare Build (Docuentation: https://github.com/cloudflare/vibesdk and Demo: https://build.cloudflare.dev/) builds applications from preconfigured (and econfigurable) instructions and agents. Generation in HTML, css,...
Trivia Pixel
Trivia Pixel (https://www.triviapixel.com/) generates quizzes based on a given theme, to be completed solo or in competition mode. Editable question...
Pandada
Pandada (https://pandada.ai/) is a chatbot that specializes in data analysis and complex searches. Numerous data conversation tools available and integrable...
Ai pdf reader
Ai pdf reader (https://aipdfreader.net/fr) summarizes pdf documents and allows them to be queried via a chatbot. No limitations spotted during...
Flames
Flames (https://flames.blue/) builds applications from an instruction. Hosting on Flames’ servers, database including if necessary for the project. Note: in...
Formhug
Formhug (https://formhug.ai/) offers the creation of forms, quizzes without or with the help of the generative AI. With, generation from...
Axell
Axell (https://www.axellai.com/) brings together several language and image/video generation models in an infinite array interface.Each generation since a chatbot integrated...
Komos
Komos (https://www.komos.ai/) is a set of agents that allow you to automate tasks on the web. Automation flows can be...
Arcanon
Arcanon (https://arcanon-ai.vercel.app/) summons the thoughts of Descartes, Artistote, Machiaviel and Han Fei around a proposed subject. In “Sessions”, between 2...
Monodesk
Monodesk (https://www.monodesk.com/) offers three project management tools linked in a single interface: calendar, Kanban board and contact/customer database. These three...
Mercury 2
Mercury 2 (description https://www.inceptionlabs.ai/blog/introducing-mercury-2 : and demo: https://chat.inceptionlabs.ai/) is the first model for text generation based on delivery, as are...
Variant
Variant (https://variant.com/) generates site or application designs from an instruction. 6 designs are generated per instruction. and positioned in a...
Anuma
Anuma (https://www.anuma.ai/) is a text and image chatbot that integrates several models in two modes: private and public. The private...
Flow + Nano Banana 2
Flow (https://labs.google/fx/fr/tools/flow/) generates sound videos from a text instruction that can be augmented with images. Images can be generated in...
Runable
Runable (https://runable.com) brings together several recent templates and agents in a single application to generate different types of text, image,...
Litgrades
Litgrades (https://litgrades.com/) generates flashcards, teacher worksheets, and review sheets from an instruction and related topics. Generations are saved and folders...
Findtube
Findtube (https://findtube.ai/) is a search engine that specializes in YouTube videos and learning modules that build on these same videos....
Gemini Music (Lyria 3)
Lyria 3 is the music generation model built into Gemini (description: https://deepmind.google/models/lyria/ and direct access: https://gemini.google.com/music). The 30-second songs can...
Deep Scholar
Deep scholar (https://deep-scholar.vercel.app, based on Lotus, open-source: https://github.com/lotus-data/lotus) is a semantic search engine coupled with a language model and focused...
Figy
Figy (https://figy.ai) generates flashcards from a document.Three types of cards are offered: questions / answers, fill-in-the-blank text and multiple choice....
Teachermatics
Teachermatics (https://teachermatic.com/) brings together a set of generators dedicated to teaching (more than 80: lesson plans, quizzes, flashcards, questions, etc.)....
Slides orator
Slides orator (https://www.slidesorator.com/) generates an explainer video with an audio 3D avatar from a pdf. From the pdf, a knowledge...
Doodle Duel
Doodle Duel (https://doodleduel.ai/) is a drawing game where you have to draw the given word or phrase as quickly as...
VoooAI
VoooAI (https://voooai.com/) generates images, videos, and music from a workflow: one instruction generates content that becomes the source of another...
Inkr
Inkr (https://inkr.app/) transcribes audio from audio or video files, a URL, or a live recording. Transcription is offered in a...
Muses
Muses (https://muses.my/) is a word processor combined with a chatbot and a library of documents, URLs, and images. From a...
Eler
Eler (https://www.eler.ai/) transforms 3D images into realistic photos. Three modes are offered: from a sjetchup file (skp), a 3D file...
Veeso
Veeso (https://veeso.ai/) generates communication content (posters, flyers, infographics, etc.) from a detailed instruction. A chatbot window with agents and reflection...
Rabbit Hole
Rabbit Hole (https://www.rabbithole.chat/) is a visual search engine that organizes the generated answers in the form of an infinite mind...
Kugel Audio
Kugel Audio (documentation: https://github.com/Saganaki22/ComfyUI-KugelAudio and demonstration: https://huggingface.co/spaces/multimodalart/kugelaudio) is a text-to-speech (text-to-voice) model with 24 European voices. Two possibilities: generation from...
Sesame
Sesame (https://www.sesame.com/) is an oral conversation model currently in research version, based on the open-source csm model (https://github.com/SesameAILabs/csm).Current research is...
Weavy
Weavy (https://www.weavy.ai/) brings together several dozen “combinable” image and video generation templates on an infinite array. From an image generated...
Parliant
Parliant (https://www.parliant.ai) is a survey and polling application where generative AI can produce the text of open-ended questions based on...
André
André (https://andre.vote/) is a chatbot specialized in electoral analysis in France and fed on 4 open data sources covering the...
Voxtral
Voxtral (documentation: https://mistral.ai/fr/news/voxtral-transcribe-2 and demo: in Mistral AI studio or for direct transcription voxtral mini realtime – out of order...
Hugging Chat
Hugging Chat (https://huggingface.co/chat/) closed in 2025 (see the HuggingChat Assistants and HuggingChat Tools archives for the previous version) is accessible...
Otio
Otio (https://otio.ai/) is a chatbot focused on document analysis and web search based on 40 language models available. Two modes...
Dokie
Dokie (https://dokie.ai/) generates presentations from an instruction or document, a URL, or a YouTube video. The generations are progressive via...
Foldback Design
Replit Design (https://replit.com/products/design) generates website or application designs from an instruction. Several agents are implemented, from statement parsing to code...
Vibe paint
Vibe paint (https://vibepaint-ai-795372324720.us-west1.run.app/) transforms a drawing made directly in the interface from a predefined style. The transformed drawing can then...
Chef by Convex
Chef by Convex (documentation: https://github.com/get-convex/chef and application: https://chef.convex.dev/) builds applications with databases from an instruction. Several language models are offered...
LLM Council
LLM Council (documentation: https://github.com/machine-theory/lm-council?tab=readme-ov-file, demonstration: https://huggingface.co/spaces/burtenshaw/karpathy-llm-council and video presentation of related research: <a href="https://www.youtube.com/watch?v=hI0XCE27QqE”>https://www.YouTube. com/watch?v=hI0XCE27QqE is a “democratic” space that...
Prism
OpenAI’s Prism (presentation: <a href="https://openai.com/fr-FR/prism/”>https://openai.com/fr-FR/prism/ and application: https://prism.openai.com/) is a LaTex editor coupled with a chatbot based on ChatGPT 5.2....
Leadde
Leadde (https://leadde.ai) generates an explainer video with avatar and voice from a document or presentation. Choice of avatar and voice,...
Mindmaclasse
Mindmaclasse (https://apps4edu.fr/mindmaclasse/) generates mind maps from an instruction or a document as well as exercises for revision (quizzes, fill-in-the-blank texts...
Cybercut
Cybercut (https://cybercut.ai/) is an AI-assisted video editing app. Three main features: Smartclip generates excerpts from a video oriented to social...
Anam
Anam (https://anam.ai) creates chatbots based on video avatars from an instruction. 8 language models, 42 avatars and 499 voices available...
Rapidnative
Rapidnative (https://www.rapidnative.com) generates mobile apps from an instruction. Error detection and correction.Object-by-object editing mode is possible.Generation in ttx.Testing and use...
Z-image
Z-image (documentation: https://github.com/Tongyi-MAI/Z-Image and Turbo version demonstration: https://huggingface.co/spaces/Tongyi-MAI/Z-Image-Turbo) is a lightweight (6 million parameters) and fast image generation model. Very...
Flux 2 Klein
Flux 2 Klein is an open-source lightweight model of Black forest LAbs from the same family as Flux 2 or...
TranslateGemma
TranslateGemma (documentation: https://blog.google/innovation-and-ai/technology/developers-tools/translategemma/ and 27B https://huggingface.co/spaces/hysts/translategemma-27b-it or 4B: https://huggingface.co/spaces/fantos/translate-gemma) is a translation template available in three sizes (4, 12, and...
ChartGen
ChartGen (https://chartgen.ai) analyzes data files and produces visualizations in the form of graphs. Two modes are available: “fast” and “reasoning”....