Skilly pricing, free plan and limits

Open-source Mac app that listens to your question, answers by voice and moves a pointer to the right button, in any app or browser tab.

Best for
Self-taught graphic designers learning Blender or Figma on Mac
Not for
Enterprise IT teams requiring SOC 2 compliance attestation or formal security audit

Should you use Skilly?

Skilly replaces tutorial hunting with a voice guide that watches your Mac screen and points at the control to click next. It works across apps, from Figma and Canva to VS Code and Sheets, and browser extensions cover web pages. Pay a small monthly fee with your own OpenAI key, or let Skilly host the model.

Animated cursor that physically moves to the exact UI element being explained — no browser-based AI assistant can do this for native Mac apps.

The animated cursor pointer and per-app SKILL.md curricula create a differentiated tutoring UX, but the barrier to replication is low since the core code is Apache-2.0 and any competitor can fork and build on it.

Also for

  • Indie SaaS founders embedding guided onboarding without a support team
  • Self-taught designers learning Blender, Figma, or After Effects on Mac who want real-time spoken guidance rather than written tutorials
Show 3 more
  • Indie macOS developers learning Xcode or VS Code workflows who prefer a voice tutor over video courses
  • Indie SaaS founders who want to embed a voice-guided onboarding experience in their web product without hiring a support team
  • Open-source contributors and AI builders who want to fork or extend a working voice-and-pointer tutoring system

Also not for

  • Windows or Linux developers who cannot run the macOS desktop tutor

Main trade-off

macOS-only personal tutor in 2026 with a 3-hour/month cap and no overflow option; Windows users cannot use the product at all.

Skilly pricing

PlanMonthly price
Free trialFree
Builders Early AccessFree
BYOK$5/mo
Hosted$19/mo
Builders Starter$29/mo
Builders Studio$99/mo
Builders Scale$299/mo
How the pricing works, in full

Personal use starts with a 15-minute hosted trial and no card. After that you choose BYOK at $5/month plus whatever your own OpenAI key spends, or Hosted at $19/month with 3 hosted hours included (about $0.11 per included minute). Skilly for Builders is a separate pilot programme: Early Access $0, Starter $29, Studio $99 and Scale $299 per month. The builder page no longer states minute allowances and says beta plans stay hard-capped.

Before you commit

  • OpenAI Realtime API tokens consumed during sessions are billed to Skilly's infrastructure, which is priced into the monthly plan, but self-hosters pay their own OpenAI usage costs on top of compute
  • 3-hour/month personal plan cap means frequent users may feel constrained with no mid-tier upgrade option between $19 and nothing

What Skilly does

Skilly is an open-source voice guide for macOS that answers questions about the app on your screen, speaks the steps back and moves a pointer to the right control. It works in any Mac app, adds app-specific skills for better lessons, and ships Chrome, Edge and Firefox extensions. Windows, Linux and mobile are on a waitlist.

  • Voice-First Screen-Aware Tutoring

    Streams your microphone audio and live screenshots to OpenAI Realtime in a single WebSocket call, cutting AI response latency roughly in half compared to traditional three-stack TTS+STT+LLM setups.

  • Animated Cursor Pointer

    Calls a point_at_element tool to physically animate a blue cursor to the exact button, panel, or control mentioned in the explanation, working across all connected monitors without requiring the user to identify it manually.

  • Per-App Teaching Curricula

    Works in any Mac app, and optional app-specific skills add lessons, interface vocabulary and current documentation so answers fit the tool on screen rather than reading like generic advice.

  • Always-On Live Tutor Mode

    Captures screenshots only while the user is speaking, so the Mac screen is not continuously recorded; users work normally and speak when they need guidance, with push-to-talk also available as an alternative.

Show all 8 features
  • Progress Tracking Across Sessions

    Saves completed lessons and curriculum stages per app locally so each new session resumes exactly where the previous one left off, rather than restarting from the beginning.

  • Auto-Language Detection

    Detects the spoken language in real time (English, Arabic, Japanese, Chinese, Spanish, and more) and replies in the same language with no settings to configure.

  • Skilly for Builders Embeddable Widget

    Lets SaaS and website owners train Skilly on their own docs via a Studio project, then deploy a branded voice-and-pointer onboarding guide on their domain, with a paid plan for teams that outgrow the free tier.

  • Fully Open Source (Apache-2.0)

    The complete codebase is public at github.com/tryskilly/skilly, allowing teams to self-host with their own OpenAI API key and inspect the code before putting it in front of users.

Works with

  • OpenAI Realtime API
  • Blender
  • Figma
  • After Effects
  • Xcode
  • VS Code
  • Photoshop

Missing integrations

  • Windows native app
  • Adobe Premiere Pro
  • DaVinci Resolve
  • Linear / Notion (productivity app curricula)

Most users expect these and they are not currently supported.

Capabilities

  • Voice AI
  • Screen watching
  • AI tutoring
  • Open source
  • macOS
  • Realtime AI
  • Education

Strengths and limits

Strengths

  • The trial needs no credit card, and the BYOK plan keeps the ongoing cost close to your own OpenAI usage.
  • The latency win over a traditional three-stack pipeline is genuinely noticeable in practice: replies feel closer to a live conversation than the stop-start pacing of most voice assistants.
  • Animated cursor that physically points to UI elements on-screen is a differentiated capability no browser-tab AI assistant (ChatGPT Voice, Gemini Live) can replicate for native Mac apps.
  • The permissive open-source license lets security-conscious teams audit the whole system, or self-host it entirely on their own infrastructure with their own OpenAI key, before ever putting it in front of end users.

Limits

  • The desktop app is Mac only (macOS 14 or later). Windows, Linux and phone versions are a waitlist, so on a PC the browser extension is all you get.
  • Monthly tutoring time is capped for the personal plan, and power users who want daily practice sessions have no overflow option once they hit the limit.
  • Relies entirely on OpenAI Realtime API, so any OpenAI outage or latency spike directly affects Skilly's reliability with no fallback provider option documented.
  • Teaching curricula exist for only 6 apps; learning Adobe Premiere Pro, DaVinci Resolve, or any non-listed tool requires writing a custom SKILL.md file.

Skilly alternatives

ToolPrice fromFree planRuns onRating
Skilly This page$5/moYesWeb · Mac--
CursorCursor puts AI coding help inside an IDE for people already writing software. Skilly instead watches the whole screen and talks you through design or developer tools you're still learning, step by step.$8/moYesWeb · iOS · Mac · Windows4.4
ChatGPTChatGPT Voice runs everywhere at $20/month but has no idea what's on your screen. Skilly stays Mac-only and limits how many tutoring hours a personal plan includes each month, trading that reach for a cursor that physically points at the UI element it's explaining.$8/moYesWeb · iOS · Android · Mac · Windows4.2
ClaudeClaude is a capable text-based assistant that runs in any browser, on any OS. Skilly stays Mac-only but adds something Claude doesn't offer at all: real-time voice tutoring that sees the screen and points at it.$20/moYesWeb · iOS · Android · Mac · Windows4.3

Skilly facts

Works offline
No
Minimum skill level
Basic
Price band
Budget
Maker founded
2025
Training-data policy
OpenAI Realtime API processes audio and screenshots during sessions. Skilly's own servers do not train on user session data. Provider API keys remain on Skilly's backend infrastructure rather than being exposed in the browser or SDK.

Data and privacy

Apache-2.0 (open source)

Questions about Skilly

What are Skilly's pricing plans in 2026?

Two personal plans follow a 15-minute free trial: BYOK costs $5 a month plus your own OpenAI bill, and Hosted costs $19 a month with 3 hours of hosted voice help. Skilly for Builders is priced apart, at $0 for early access, then $29, $99 or $299 a month for Starter, Studio and Scale.

Can you use Skilly without paying?

Only briefly. The Mac app includes 15 minutes of real hosted use with no card, and builders accepted into the pilot can start at $0 on Early Access. Ongoing personal use costs at least $5 a month on BYOK. The code is open source, so a developer can also inspect or build it.

Which tools compete with Skilly in 2026?

Gemini Live is the closest cross-platform alternative if you don't need an app-specific cursor pointing at UI elements. Clicky, the MIT-licensed project Skilly was forked from, is worth trying if you want the simpler original push-to-talk flow without curriculum tracking. For coding-specific help inside an IDE rather than a general creative-app tutor, Cursor is the stronger pick.

Skilly or ChatGPT Voice: which should you pick?

ChatGPT Voice runs on macOS, Windows, iOS, and Android and costs $20/month for its unlimited Pro plan, but it cannot see your screen or point at anything on it. Skilly's desktop app runs only on macOS (Chrome, Edge and Firefox extensions cover web pages) and the Hosted plan includes 3 hours a month, trading platform reach for screen awareness: it watches what you're doing and physically moves a cursor to the exact button or menu it's talking about. Pick ChatGPT Voice for general-purpose conversation on any device; pick Skilly when you need hands-on guidance inside a specific Mac app.

How long does it take to get going with Skilly?

A first Skilly session starts within a couple of minutes of downloading it: grab the macOS app from tryskilly.app and open it from the menu bar to begin the free trial. Open any app you want help with, Figma or VS Code for example, start talking, and Skilly listens, captures your screen, and speaks back while pointing its cursor at what it means. Teams building Skilly for Builders instead create a free Studio account, upload their own docs or a website URL, and copy a JavaScript snippet onto their site.

About Skilly

Skilly is a voice-first AI tutor for macOS built by indie developer Mohamed, released as an open-source fork of Farza Majeed's Clicky project under the Apache-2.0 license. The app lives in the Mac menu bar and pairs a live screen feed with OpenAI's Realtime API, so the tutor can see what you're doing and answer out loud without you ever switching windows.

Read the full background

The core mechanic is a pluggable teaching layer: every supported app gets its own SKILL.md curriculum, so the coaching stays specific to the software in front of you instead of offering generic tips that don't match what's on your screen.

Skilly for Builders extends the same voice-and-cursor mechanic to a company's own product: product owners load their own documentation into a Studio project, lock the widget to their domain, and ship a branded onboarding guide inside their web app without exposing provider credentials to the browser.

Sources and guides

More AI Tools on Hokai

  • Bland AIEnterprise voice AI platform for phone agents: $0.12 to $0.14 per minute, LLM, speech and transcription included, 1 million concurrent calls claimed.
  • SesameVoice-first personal agents on iOS and Android: Maya, Miles, Simone and Charlie, each with its own memory. Free in preview, glasses due in 2027.
  • ElevenLabsAI voice platform for text-to-speech, voice cloning, dubbing, music and conversational voice agents
  • SpekoHosted router that sends speech-to-text, LLM and text-to-speech calls across 106 voice AI models, with failover and per-language benchmarks.
  • NextPhoneAI receptionist for law firms and service businesses: answers every call 24/7, books into your calendar, on flat monthly plans with unlimited calls.
  • DeepgramReal-time voice AI APIs for developers: speech-to-text under 300ms, TTS, and voice agents. Used by 200,000+ developers.