iisee.me vs Speech To Markdown: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of iisee.me and Speech To Markdown — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
iisee.me
Charlie Clark (GitHub: charlieclark)
Web app to create customizable AI-generated expression grids for design, character exploration, and visualization.
Key features
- Expression Grid Generation: Creates a multi-cell grid of AI-generated images showing variations in expression, pose, or style to support rapid visual ideation.
- Interactive Web Editor: Web-based interface for previewing grids in real time and adjusting generation parameters without local tooling.
- Customizable Parameters: Controls for seed, style, intensity, and layout to fine-tune how expressions and visual characteristics vary across the grid.
- Export and Sharing: Options to export generated grids (image download or shareable link) for integration into design workflows or reviews.
- Preset Templates: Ready-made templates for common grid layouts and expression sets to accelerate creation for character design and reference.
- Open-Source Repository: Public GitHub repo enabling developers to self-host, inspect generation logic, or extend functionality for bespoke needs.
- Generate AI-created expression grids (collections of expressions/images)
- Web-based frontend built with Next.js
- Database schema defined with Prisma
- Repository includes npm scripts for setup (npm install) and database start (npm run db:start)
- Deployment configuration present (vercel.json) for easy Vercel hosting
- Scripts for database migration and startup (start-database.sh, db-deploy-migrations.sh)
- Source code available on GitHub for self-hosting and extension
Best for
- Character Design Ideation: Quickly generate a matrix of facial expressions to iterate on character looks for games, comics, or animation.
- Animation Reference Sheets: Produce consistent expression grids to guide animators and ensure continuity across scenes.
- Avatar and Emote Creation: Create multiple emotive avatar variants for chat apps, streaming, or social platforms.
- UX and Concept Testing: Generate visual variations for user testing to evaluate emotional impact or recognizability of character designs.
- Marketing Creative Exploration: Rapidly prototype visual concepts showing different emotional tones for ad or social creatives.
- Educational and Reference Material: Produce expression collections for teaching acting, emotion recognition, or illustration techniques.
- Create expression/pose sheets for character design and animation
- Rapidly prototype facial expression variations for game or film art
- Generate visual assets for avatars or social media content
- Self-hosted research or experimentation with image-generation workflows
- Integrate into artist pipelines by extending Next.js API routes or the source code
Speech To Markdown
xajik
Free, 100% local macOS menu-bar app that turns speech into structured markdown using whisper.cpp and any local LLM.
Key features
- 100% Local Pipeline: Runs whisper.cpp for speech-to-text and any local LLM server for structuring — no cloud calls and no API keys required.
- Global Dictation Hotkey: Press ⌘⌥] in any app to have the transcript typed straight at your cursor, works in Terminal, browser, Slack, and more.
- Agent Mode Live Structuring: A floating capsule streams your voice through the LLM into a real-time Markdown, plain text, or HTML document.
- One-Line Install: A single curl-piped script installs xcodegen, whisper-cpp, and ffmpeg via Homebrew, then builds the app from source into /Applications.
- iOS Companion: A fully offline iPhone/iPad app that uses Apple Intelligence on iOS 26+ (iPhone 15 Pro and up).
- Multiple Output Formats: Format, edit, or append the LLM output as Markdown, plain text, or HTML from a single control panel.
- Send-Now Flush: The Send (⏎) control flushes the current buffer to the LLM immediately instead of waiting for the pause/word-count threshold.
- Model Picker: Download and swap Whisper models from Settings — Base (~150 MB) is a good starting point.
Best for
- Private Meeting Notes: Dictate meeting recaps on a Mac with sensitive content that must never leave the device.
- Voice-Driven Coding Comments: Speak function docstrings or PR descriptions into your editor at the cursor via Global Dictation.
- Structured Journaling: Use Agent Mode to ramble freely and get a clean, headed Markdown document out in real time.
- Offline Field Notes on iOS: Capture voice notes on an iPhone with no signal, structured into markdown using on-device Apple Intelligence.
- Slack / Email Long-Form: Dictate long replies straight into Slack or Mail without opening a separate transcription tool.