Search the site's AI modules, directories, and articles by keyword to find the matching feature or content.

Site Default Model

An autonomous AI agent with multi-round reasoning and tool use that breaks down and completes complex tasks.

Card-based notebook manager for organising reading, research, and project notes.

Build a private knowledge base; AI conversations cite your internal docs automatically.

Build your own chatbot; configure role prompts and knowledge bases for domain-specific AI.

Google Gemini 4 Argon, Google's newest flagship reasoning model, built for complex coding, expert knowledge work and deep multi-step reasoning.

Google Gemini 3.8 Flash, Google's most intelligent Flash model with major gains in coding, agentic tasks, and multi-step reasoning.

Ultra-low-latency real-time voice conversation powered by Google Gemini 3.8 Live, with automatic multilingual switching, barge-in support and transcripts for both sides.

Real-time voice conversation powered by Google Gemini 3.8 Live Extended Thinking, with deeper multi-step reasoning, a selectable thinking level and spoken progress updates while it thinks.

Google Gemini 3.6 Flash, the newest fast general-purpose Gemini model at a lower cost.

Google Gemini 3.5 Flash Lite, the fastest and most affordable tier of the Gemini 3.5 family.

Google Gemini 3.1 Pro, the flagship Gemini model via Google AI Studio.

Low-latency real-time voice conversation powered by Google Gemini 3.1 Flash Live, with barge-in support and transcripts for both sides.

Google Gemini 3.1 Flash Lite, the fastest and most affordable Gemini tier.

Anthropic Claude Fable 5.1, the newest top-tier Claude model, with stronger long-horizon agentic work, multistep research, and document, spreadsheet, and slide work.

Anthropic Claude Fable 5, the most powerful Claude model, a new tier above Opus.

Anthropic Claude Opus 5.5, the new-generation flagship for long-running agentic coding and knowledge work, performing at the level of Fable 5.1 on most work.

Anthropic Claude Opus 5, the new-generation flagship with a large jump in coding, reasoning, and computer use.

Anthropic Claude Opus 4.8, the flagship of the Claude 4 family, with sharper judgment and improved honesty.

Anthropic Claude Sonnet 5.5, the new-generation mid-tier model with the best combination of speed and intelligence, with major gains in coding and knowledge work.

Anthropic Claude Sonnet 5, a balanced mid-tier model with strong reasoning and writing quality.

Anthropic Claude Haiku 5.5, the new-generation lightweight model: the fastest and most capable small Claude model, built for high-volume classification, summarization, and extraction.

Anthropic Claude Haiku 4.5, the fastest and cheapest Claude model.

OpenAI GPT-6 Astra — the most capable model, built for the hardest end-to-end work, 1.05M context and 128K max output.

OpenAI GPT-6.1 Sol — near-Astra performance for complex work at a lower cost, 1.05M context and 128K max output.

OpenAI GPT-6.1 Terra — a fast, efficient model for visual reasoning, precise computer use and clear, natural writing, 1.05M context and 128K max output.

OpenAI GPT-6 Sol — built to power complex coding and agentic workflows, 1.05M context and 128K max output.

OpenAI GPT-6 Luna — the most efficient GPT-6 model for focused, high-volume tasks, 1.05M context and 128K max output.

OpenAI Decisions API with GPT-6 Luna — typed decisions about text or images: the probability that a condition holds, one option from a fixed set, or a score against ordered levels.

OpenAI GPT-5.6 Sol — frontier flagship for complex professional work, 1.05M context and 128K max output.

OpenAI GPT-5.6 Terra — balances intelligence and cost for general-purpose tasks.

OpenAI GPT-5.6 Luna — built for cost-sensitive, high-volume workloads.

OpenAI ChatGPT 5.5 — flagship with 1.05M context and 128K max output.

OpenAI ChatGPT 5.4 mini, a lighter and cheaper variant of GPT-5.4.

OpenAI ChatGPT 5.4 nano, the smallest and fastest 5.4-family model.

Perplexity Sonar Deep Research runs a multi-step research workflow: planning, iterative searching, cross-referencing, and synthesis.

Perplexity Sonar Reasoning Pro combines live web search with deeper reasoning.

Perplexity Sonar Pro, a web-search-augmented LLM.

xAI Grok 4.7, the newest flagship Grok model with a 500K context window and an xhigh reasoning-effort level for the hardest problems.

xAI Grok 4.6, a flagship model for coding, agentic tasks, and knowledge work, with a 500K context window.

xAI Grok 4.5, flagship model with strong reasoning and a 500K context window.

Meta Muse Spark 1.3 — the latest Muse Spark model, tuned for agentic workflows and coding, with image understanding, reasoning effort, web search, and a 1M context window.

MoonshotAI Kimi K3 flagship model with vision and a 1M-token context.

Z.ai GLM 5.2 large-scale reasoning model with a 1M-token context.

Alibaba Qwen 3.5 MoE (397B total, 17B active).

Upload documents or paste text, and the AI splits the content into knowledge blocks by chapter, paragraph, or concept, showing the result in JSONL format and producing a downloadable JSONL file.

Paste a meeting transcript (from speech_to_text or manual notes) and receive a clean summary with key decisions, action items, and follow-up dates.

Turns scattered class, reading, research, or meeting notes into clear, well-structured key-point notes.

One-click slide outline generator.

Plans and generates an A4-landscape editable PPTX deck with an AI Agent workflow.

Generate a 20-slide pptx deck via gamma.app.

An AI copy-editor.

Generates Taiwan-style official documents following the standard format and phrasing conventions.

This module can only answer questions about the text in a PDF. To ask about images inside the PDF, please: 1. Use AI Agent instead 2. Use AI Agent Notebook instead 3. Use another module to extract the PDF content first

An AI homework assistant that explains solutions step by step.

Takes your draft social-media post and rewrites it for higher engagement.

Contract review assistant.

Structured report writer.

Paste a URL and receive a concise summary of the page's key points.

Enter keywords to find related web pages via Google Search — returns titles, snippets and clickable URLs.

Enter keywords to find related news via Google News — returns titles, sources, publish times and clickable links.

Academic paper assistant.

Cloud speech recognition powered by OpenAI's gpt-4o-transcribe model, with plain-text transcript and SRT subtitle output.

Cloud speech recognition with OpenAI's next-generation gpt-transcribe model — upload audio, get a high-accuracy plain-text transcript.

Cloud speech recognition with OpenAI's whisper-1 model — a transcript and SRT subtitles, with the actual time of every sentence and word.

Multi-speaker speech recognition powered by OpenAI's cloud gpt-4o-transcribe-diarize model, labeling each speaker in the transcript automatically.

Programming assistant that answers coding questions, explains errors, reviews snippets, and suggests refactors.

Project plan generator.

Rewrites event material into formal written press-release style, suitable for media outreach, internal newsletters, and PR distribution.

Adapts news material into a spoken-word broadcast script — short sentences, natural rhythm, easy to read aloud.

Upload an image or screenshot; AI extracts editable plain text via OCR.

Upload documents and an AI Agent OCRs them page by page into an editable Markdown file, with figure crops, captions and formatted tables.

Upload documents and an AI Agent OCRs them page by page into an editable Word (.docx) file, with embedded figure crops, captions and real Word tables.

Paste any article and receive an AI-vs-human authorship likelihood score with per-paragraph breakdown.

Long-form summarizer that distills your input down to approximately 500 Chinese characters (or equivalent English).

Detailed summarizer targeting ~1,000 Chinese characters.

General-purpose writing optimizer.

AI essay grader that assigns A / B / C / D / E with specific feedback on structure, content, and language.

Enter a URL to crawl the page and get its url, title, description, keywords, publish time, fetch time and the noise-free full text.

This module can only extract text from documents. For text recognition in images, please use other modules.

Image generation powered by OpenAI's gpt-image-2.6-flare (GPT Image 2.6 Flare), built for fast iteration with cleaner layouts for posters and product images, selectable output quality (auto, low, medium, high, xhigh, max), and image editing with continuous refinement.

Image generation powered by OpenAI's gpt-image-2.5-flare (GPT Image 2.5 Flare), the fastest model in the GPT Image 2.5 family for high-quality everyday images, with selectable output quality (auto, low, medium, high, xhigh, max) and image editing with continuous refinement.

Image generation powered by OpenAI's gpt-image-2.6-sunburst (GPT Image 2.6 Sunburst), built for detailed visual work with better consistency for characters and products across edits, selectable output quality (auto, low, medium, high, xhigh, max), and image editing with continuous refinement.

Image generation powered by OpenAI's gpt-image-2.5-sunburst (GPT Image 2.5 Sunburst), the next-generation flagship after GPT Image 2 with sharper detail, richer lighting and stronger prompt adherence, selectable output quality (auto, low, medium, high, xhigh, max), and image editing with continuous refinement.

Nano Banana 2.1 image model (gemini-nano-banana-2.1): more efficient than Pro with better image quality and prompt adherence, plus upload-based editing and continuous conversational refinement.

Nano Banana Pro image model with upload-based editing and continuous conversational refinement.

Nano Banana 3.1 Flash, the lightweight tier with continuous conversational refinement.

Upload any image and the model reverse-engineers the prompt that would recreate it.

Google Gemini Omni Flash 1.2, the generally available natively multimodal video generation model: create short videos with native audio from text prompts (10 seconds by default, up to 15) at 720P, 1080P, or 4K in 16:9 or 9:16, upload one to six PNG/JPG images as references (image-to-video, first/last frame interpolation, or subject references) or one MP4 video to edit or extend, and refine results with multi-turn conversational editing.

AI music generator.

Upload a song and AI continues it from the end, automatically merged into one full track.

Upload a song or instrumental track to change its style or instruments, or add vocals to instrumental music.

Upload a voice sample and AI sings a song with your voice.

Upload a song and split it into separate vocal and instrumental tracks.

Upload a person photo and then a clothing image, optionally with extra instructions, and the model dresses the person in the target outfit while keeping pose and face intact.

BytePlus Dola Seedream 5.0 Pro text-to-image, a flagship image generator with precise editing control, excellent Chinese prompt understanding, strong photo-realism, and continuous conversational refinement.

BytePlus Seedance 2.5 multimodal video generation with up to 50 reference assets, video editing, and 720P / 1080P output.

BytePlus Seedance 2.0 text-to-video.

A themed video generator that turns a name into a personalized motivational clip.

One-click Christmas greeting video generator.

Chinese New Year greeting video generator.

Turn text into studio-quality natural speech with Google Gemini 3.8 Flash TTS; choose from 30 voices and set the spoken language and delivery style.

Quickly turn text into natural speech with Google Gemini 3.8 Flash-Lite TTS; choose from 30 voices and set the spoken language and delivery style, ideal for high-volume generation.

Quickly turn text into natural speech with Google Gemini 2.5 Flash TTS; choose from 30 voices and set the spoken language.

Turn text into natural speech with Google Gemini 2.5 Pro TTS; choose from 30 voices and set the spoken language.

BytePlus seed-tts text-to-speech.

Generate sound effects and speech from a text description; optionally upload reference audio clips or one image to guide the timbre and mood.

Upload a 10-15 second sample of a person's voice and the model learns the timbre, then reads any text you provide in that cloned voice.

Translates text in any supported language into Traditional Chinese suitable for Taiwan/HK readers.

Translates English military documents into Traditional Chinese using the official MND US-China Military Terminology Dictionary.

Translates text (especially Chinese) into natural American English.

English grammar and style checker.

Practice conversation with Sophie, a friendly female AI tutor. Replies are short text answers plus synchronized voice narration.

Practice conversation with Alex, a friendly male AI tutor. Replies are short text answers plus synchronized voice narration.

A phone-friendly travel translator that turns speech into bilingual text in real time, and translates typed or dictated text and reads it aloud with one tap, in more than 70 languages.

Real-time speech translation across 70+ languages powered by Google Gemini 3.5 Live Translate, with low-latency translated audio and transcripts.

Low-latency streaming speech recognition with OpenAI's gpt-live-transcribe — the transcript appears as you speak.

A quick Simplified-to-Traditional Chinese converter.

A quick Traditional-to-Simplified Chinese converter.

Scans your text for simplified-Chinese characters and mainland-specific phrasing, highlighting each finding.

Finds typos in your text, including wrong, missing, extra, or swapped characters and punctuation errors, with corrections.

Health-education assistant for generating patient-friendly explanations of medications, procedures, and care instructions.