DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to fix a misspoken word in your own voice with Yap

Regenerate one misspoken phrase in your voice with a local model instead of re-recording the whole take.

  • Content
  • Advanced
  • 30 minutes
  • From the README
  • Claude Code
  • Codex

Voice cloning. This use case generates speech in the speaker's own voice, so only do it with recordings of your own voice or with clear permission from the speaker.

Who it is forA creator or presenter who misspoke one word in an otherwise good recording and does not want to re-record it.

The problemRe-recording a whole take to fix one word wastes time and can make the rest of the take harder to match.

The outcomeThe misspoken phrase is replaced in your own voice, and the edit is saved as a revision you can undo.

What you need first

  • An Apple Silicon Mac running macOS 26 or newer
  • Claude Code, Codex or another AI agent harness
  • Permission to record the screen, microphone and optional camera when the app asks
  • Accessibility permission only if you want ⌥⇧V to paste the prompt for you

Steps

  1. Record the take with ⌥⇧S, or import a video you already have.
  2. Wait for the automatic transcription, then find the phrase that was misspoken.
  3. Tell your agent the correct word, for example 'I said version three at 0:42 but meant version two'.
  4. Ask the agent to regenerate that phrase in your voice with the local model.
  5. Preview the revision and undo it if the replacement does not sound right.

Prompt for your agent

Using the Yap CLI and skill, find the phrase at <timestamp> in recording <recording ID> and regenerate it in the speaker's own voice, replacing the word <wrong word> with <correct word>. Report the revision ID and confirm by previewing that only that phrase changed.

Caveat. The voice model runs locally on your Mac, and the source recording stays byte-for-byte as you captured it.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page