AI Blocks › Turn speech into text and back
Voiceover maker
Give it your text. Get spoken audio in a built-in voice, for narration, voiceovers or batches.
Voiceover maker is a free AI skill for the job "Turn speech into text and back". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · Apache 2.0 licence · Made by OpenAI · Level: beginner · Thinking: low
Made by OpenAI. See the original on GitHub; we copied it as it is, with its licence.
What it does
Spoken audio from your text, in a built-in voice, ready for narration, product demos, phone menus or accessibility reads. You can make one clip or a whole batch in one run. You give the exact text, a voice, the delivery style, such as calm or upbeat, and a file format. The skill writes a short labelled brief for the speech model without changing your words. For many lines, it writes a batch file with one job per line and runs it once. It then listens for clarity, pacing and pronunciation, changes one thing at a time, and saves clean files with stable names. It needs Python and an OpenAI API key.
You give it
- The exact text to speak
- A voice and delivery style
- File format and where to save it (optional)
- An OpenAI API key
You get
- One or more audio files
- A record of text, voice and settings used
- A check of pacing and pronunciation
- A re-run with one tweak if needed
Use it when
- You need narration for a video or slide deck.
- You want to record a set of phone menu prompts.
- You need an audio version of an article.
- You want to hear several voices or speeds before choosing.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run code and reach the OpenAI Audio API.