Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    vi Say

    1

    Turn GitHub projects, websites, articles and recordings into narrated explainer videos, dynamic visuals and multi-format posters.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    vi-say

    vi-say

    Example session with this skill installed

    Illustrative request: Use $vi-say to introduce Handy (https://github.com/cjpais/Handy), a desktop speech-to-text app. Prepare a Chinese-language explainer, promotional posters in 4:3, 3:4 and 16:9, and publishing copy.

    • Read your context and instructions
    • Compiled the vi-say

    Real example: Handy

    These are existing vi-say project assets; the example request is reconstructed, not an original session transcript.

    Posters

    • 4:3 poster
    • 3:4 poster
    • 16:9 poster

    Publishing copy

    标题:想法太快,打字太慢?试试 Handy

    话都想好了,还得一个字一个字敲出来。写邮件、记灵感、整理待办的时候,能不能直接说?

    这次分享一个免费开源的桌面语音输入工具:Handy。点进输入框,按住快捷键说话,松开后就能把识别出的文字粘贴进去。

    它还有一个特点:本地转写。先下载合适的模型,之后日常识别可以离线完成,录音不用为了转写上传云端。

    这期视频把基本用法和第一次使用要做的设置过了一遍。中文输入记得选支持中文的模型,先录一句试试;专有名词和标点,最后再检查一下。

    如果把打字换成说话,你最想用在哪个场景?欢迎留言,觉得有用记得点赞、关注。

    项目:https://github.com/cjpais/Handy
    官网:https://handy.computer

    #Handy #开源工具 #语音输入 #效率工具

    Connects securely to your tools. The creator never sees your data.

    About this skill

    vi-say (Visual + Say) is an AI agent skill for turning source material into visual stories. Give it a GitHub repository, website, article, recorded video or topic, and it guides production from research through delivery.

    What you can create

    • Explainer videos and dynamic demonstrations with scripts, storyboards, subtitles and publishing copy.
    • Separately composed 4:3, 3:4 and 16:9 posters, with visual direction presented early in the workflow.
    • Product introductions using real screenshots when available, diagrams, comparisons and a configurable example dragon presenter.
    • Narration using original audio or an authorized local voice reference.

    How it works

    1. Research the source and identify the audience and key message.
    2. Develop poster direction, script and storyboard.
    3. Prepare audio, captions, visuals and animation, then render and review deliverables.
    4. Package the final video, posters, narration and publishing copy as appropriate for the task.

    Requirements and limitations

    Editing and rendering require Python, Node/npm, FFmpeg, suitable fonts and relevant dependencies. Local narration requires a compatible model and an authorized reference voice. The default complete character and Remotion editorial video layouts are 16:9; vertical video needs additional layout work. Automated checks do not replace visual or audio review. Workflow documents and bundled examples are primarily in Chinese; specify your desired narration language.

    Created by Anthony Li.

    Rendering requires Python, Node/npm, FFmpeg, suitable fonts and dependencies. Local narration needs a compatible model and an authorized reference voice. Default full character and editorial video layouts are 16:9; vertical video requires additional implementation. Automated checks do not replace visual and audio review.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 12 days ago

    Requires

    Python
    Node.js / npm
    FFmpeg
    Suitable fonts
    Remotion-compatible browser
    macOS

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Write Files
    Environment Variables
    Listed12 days ago

    What's inside

    Frequently Asked Questions

    vi-say guides research, scripting, storyboards, audio, visuals and delivery through a structured workflow. Final visual and audio quality still require review.

    Video editing and rendering require Python, Node/npm, FFmpeg, suitable fonts and the relevant dependencies. Local narration also requires an authorized voice reference and a compatible model.

    Yes, the agent generates pre-production posters in three different aspect ratios, allowing you to validate branding and visual tone before the full video production begins.

    The skill package includes an 11-stage workflow, scripts, Remotion resources, a replaceable example dragon character, and templates.

    vi-say provides a structured production workflow, reusable assets and scripts for audio timing, captions, animation and checks. Synchronization and visual quality should still be reviewed in the actual output.

    The skill supports parsing GitHub repositories, live URLs, and existing raw video files to distill content into structured scripts and storyboards.

    New in Agents & Orchestration