Screen and voice recording
Capture what is happening on your screen while explaining it aloud, using macOS microphone and screen-recording access.
CAKIE
CAKIE is a Mac app for recording your screen and voice for an AI agent, with transcripts, screenshot highlights, and easy prompt copying.
Screen recording for AI agents
CAKIE is a Mac screen-recording app designed for giving AI agents visual and spoken context. Instead of describing a screen state only in text, you record the screen while talking through what you want the AI to understand.
After recording, CAKIE provides a transcript and screenshot highlights. You can review the video, highlights, and transcript, then use Copy Prompt to paste a handoff into an AI agent. The workflow is intended for situations where a written request alone does not adequately convey what is on screen or which details matter.
Features
Automatic transcript
Review a text version of the spoken explanation alongside the recording before handing it to an AI agent.
Screenshot highlights
CAKIE provides screenshot highlights that point an AI to relevant visual context from the recording.
Copy Prompt workflow
Use the built-in Copy Prompt action to create a handoff containing references to the transcript, highlights, and saved video.
Review and attachment options
Switch between Video and Highlights while reviewing the result, and attach screenshots when an AI app cannot access local files.
Use cases
Explain a visual edit
Show an AI agent a website, app, or interface while narrating the change you want, so the request includes both the visible design and your verbal direction.
Provide context for a complex screen
Walk through a screen with several relevant details and use screenshot highlights to preserve the parts the AI should consider when responding.
Document a workflow or issue
Record a task or problem as it happens instead of reconstructing the sequence in text, then paste the resulting prompt into an AI agent for assistance.
Prepare a checked AI handoff
Review the video and transcript before sending a request, correcting or withholding the handoff until the intended context is clear.
Pros and Cons
Pros
- Combines a screen recording and spoken explanation in one handoff for an AI agent.
- Adds a transcript and screenshot highlights to make visual context easier to review.
- Lets users inspect the video, highlights, and transcript before sharing.
- Supports a copy-and-paste workflow, with screenshot attachments available when an AI app cannot access local files.
Cons
- The product is currently presented as a Mac app; support for other platforms is not documented.
- The site does not provide pricing details on a valid pricing page.
- Some optional online AI features may send the text and images needed for those features through CAKIE's servers to AI providers.
FAQ
What does CAKIE do?
CAKIE is a Mac app that records your screen and voice, then adds a transcript and screenshot highlights so an AI agent can follow the explanation.
How do I share a recording with my AI?
Record and review the video, then select Copy Prompt and paste the generated prompt into your AI agent. The prompt references the transcript, screenshot highlights, and saved video.
Does my recording stay on my Mac?
Recording and transcription happen on your Mac. If you enable optional online AI features, the text and images needed for those features may be sent through CAKIE's servers to AI providers.
Can I review a recording before sharing it?
Yes. You can switch between Video and Highlights and review the transcript before sharing. Nothing is shared with another app until you paste or attach it there.
Which platforms does CAKIE support?
CAKIE is a Mac app and uses macOS microphone and screen-recording permissions to capture your voice and on-screen context.
Quick Facts
- Category
- AI productivity and screen recording
- Platform
- Mac app
- Primary workflow
- Record, review, copy prompt, then paste into an AI agent
- Outputs
- Saved video, transcript, and screenshot highlights
- Permissions
- macOS microphone and screen recording
- Pricing
- Not documented on the available pricing page
CAKIE Alternatives
SpeakoFlow
SpeakoFlow is a free, open-source desktop voice-to-text app for Windows, macOS, and Linux. Dictate into any app, use Flow, cleanup, translation, and a screen-aware assistant.
QuickQuill
QuickQuill is a local-first macOS dictation and transcription app to record meetings, summarize audio, and export notes without the cloud.
Zen Whisper
Zen Whisper is a local-first dictation and transcription app for Apple Silicon Macs on macOS 14+. Dictate into most Mac text fields and transcribe media or supported public links across 110 languages.
Capso
Capso is a native macOS screenshot and screen recording app for capturing, annotating, recording, and extracting text from screen content. Free forever, open source, and an alternative to CleanShot X.
Speech to Text Converter
Speech to Text Converter is a browser-based transcription tool for live dictation and uploaded audio or video files. Free for short tasks, Pro offers unlimited transcription, AI summaries, translation, speaker ID, and advanced exports.
Flunkey
Flunkey is a voice-first productivity layer for Windows that turns speech into text, AI outputs, and remembered context without leaving your app.