Skip to content
Recaply.
Sign inSubmit a tool

DirectorySkills

Full size
Run 1Voice note to text“In talk.mp4, turn "written updates on Friday" into a voice note that lands in the team board.”
Runs in
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • GitHub Copilot
  • OpenCode
Generates with
Your agent's model
Tested with
Claude Code 2.1.322Claude Sonnet 5.51 real run, 9 Nov
Needs
Node 22+Chromeffmpeg
Licence
Recaply licence

Voice Note to Text

A waveform listens, their words type out under it, then a chip shows where the words went.

$9.99once, yours to keep

Every premium skill and prompt, one plan$19.99 a month. Cancel any time. What you get when you buy

Payments are non-refundable. See our Terms of service.

Adds a voice note to a talking-head video: a waveform listens, the words they spoke type out underneath, then a chip shows where they landed (a task, a note, a message). Timed to the words they say, on their own footage, with their sound kept; 16:9, 9:16, 1:1 or 4:5. Renders locally with Chrome and ffmpeg: no video model, no key and no cost. Use when someone shows dictation, a voice assistant or a voice-to-task tool, or wants a spoken line turned into text on screen.

By RecaplyUpdated 11 Nov

Install Voice Note to Text

After the download, ask your agent to add it, or run the line yourself.

Read https://recaply.co/skills/voice-note-overlay/install.md and follow it to install the voice-note-overlay skill from voice-note-overlay.zip.

Paste it into your agent. It reads our install steps, finds the ZIP you downloaded and adds the skill for you.

New to skills? How to install a skill

Similar skills

All 735 skills

Who Voice Note to Text is for

What you get

  • Your video with the overlay timed to the words, sound kept
  • A voice-note card shows a moving waveform, then their words type out word for word, then a small chip lands: "Added to Tasks"
  • 16:9, 9:16, 1:1 or 4:5

Good fit

  • When someone shows dictation, a voice assistant or a voice-to-task tool, or wants a spoken line turned into text on screen

Not for

  • Footage with nobody speaking
  • Cutting or re-editing the video itself

About this skill

You say

In talk.mp4, turn "written updates on Friday" into a voice note that lands in the team board.

It said back

I rendered the video with the voice note added: talk-graphics.mp4 in the working folder. It is 1920x1080 at 30 fps and 24.3 s long. I viewed the settled-frame check sheet, not the finished video itself.

  • Beat: one voice note runs from 11.2 s to 15.2 s, starting as she says "Written updates on Friday". A waveform plays, "Written updates on Friday" types out, and a chip lands reading "Added to Team Board".
  • Layout: the speaker slides to the right half and the card fills the left. The check found no layout problems and her face stays clear.
  • Look: paper, the warm off-white panel with a tomato accent. I set the face position to [50, 30] from the face-check frame.
  • Sound: her audio is unchanged.
  • Wording: the typed words are hers. "Team Board" in the chip is my wording for her "one shared board", not something she said.
Show more

What it did in run 1

  1. voice-note-overlay
  2. ls; S=.claude/skills/voice-note-overlay; node $S/scripts/check.mjs
  3. ls -a && node .claude/skills/voice-note-overlay/scripts/check.mjs
  4. echo '{"video":"talk.mp4","transcript":"talk.json"}' > overlay.json && node .claude/skills/voice-note-overlay/scripts/overlay.mjs overlay.json --words
  5. cat > overlay.json <<'E' { "video": "talk.mp4", "transcript": "talk.json", "look": "paper", "beats": [ { "beat": "voice", "cue": "Written updates on Friday", "text": "Written updates on Friday", "to": "Added to Team Board", "for": 4 } ] } E node .claude/skills/voice-note-overlay/scripts/overlay.mjs overlay.json --face
  6. ./face-check.png
  7. ./overlay.json
  8. node .claude/skills/voice-note-overlay/scripts/overlay.mjs overlay.json --face 12
  9. ./face-check.png
  10. sed -i '' 's/"look": "paper",/"look": "paper",\n "face": [50, 30],/' overlay.json && node .claude/skills/voice-note-overlay/scripts/overlay.mjs overlay.json --check
  11. ./overlay.json
  12. node .claude/skills/voice-note-overlay/scripts/overlay.mjs overlay.json --check
  13. ./overlay-check.png
  14. node .claude/skills/voice-note-overlay/scripts/overlay.mjs overlay.json
  15. Done

9 Nov 2026 · Claude Code 2.1.322 with Claude Sonnet 5.5 · 1 min 50 s · $0.13 of API use

Questions

Is Voice Note to Text free?

No. Voice Note to Text costs $9.99 once and stays in your Recaply account, or it comes with the Recaply plan ($19.99 a month), which opens every premium skill and prompt.

Which agents can use Voice Note to Text?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

What do I get when I buy Voice Note to Text?

A ZIP of the whole skill folder (105 KB): the SKILL.md your agent follows and its 12 other files, the references, templates and scripts it uses. You download it from this page whenever you need it, and install it in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. The Recaply plan opens it too, with every other premium skill and prompt.

How do I install Voice Note to Text?

Buy it, then download the ZIP from this page. For Claude Code, unzip it into .claude/skills/ in your project. For Codex, Cursor and Gemini CLI, unzip it and run npx skills add ./voice-note-overlay with your agent's flag.

What do I get from Voice Note to Text?

Your video with the overlay timed to the words, sound kept. A voice-note card shows a moving waveform, then their words type out word for word, then a small chip lands: "Added to Tasks". 16:9, 9:16, 1:1 or 4:5.

What does Voice Note to Text need?

Node 22+, Chrome and ffmpeg, and no API key. Each use costs nothing beyond your agent.

How big is Voice Note to Text?

13 files, about 79,929 tokens in all. The SKILL.md is about 2,266 tokens, and your agent reads it only when the job fits.

What does a run cost?

Our 1 runs took 1 min 50 s to 1 min 50 s and $0.13 to $0.13 of API use each, in Claude Code with claude-sonnet-5-5. On a Claude plan, a run counts toward your usage instead.

Do I have to name Voice Note to Text to use it?

Type /voice-note-overlay first to make sure it loads. Without it, Claude Code may judge a small job simple enough to do without the skill.