AI Blocks › Turn speech into text and back
Subtitle and transcript maker
Give it a recording or video. Get a written transcript with who spoke, word timing and subtitles.
Subtitle and transcript 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 · MIT licence · Made by ElevenLabs · Thinking: low
Made by ElevenLabs. See the original on GitHub; we copied it as it is, with its licence.
What it does
Turn a recording into a written transcript with who said what, the time of each word, and subtitles ready to use. It handles meetings, interviews and videos. The skill sends audio or video to ElevenLabs speech to text, which needs an account and an API key, with Python or JavaScript code. You can switch on speaker labels, word-level timestamps, language detection and key term hints for names and jargon. It handles files with separate audio channels, lists the formats it accepts, and explains how to read the response and handle errors. It also covers live transcription and how to watch your costs.
You give it
- An audio or video file
- An ElevenLabs API key
- Names and jargon to watch for (optional)
- The language, if known (optional)
You get
- A full text transcript
- Speaker labels
- Word-level timestamps
- Subtitle output
- A cost estimate
Use it when
- You recorded a meeting and need minutes with names attached.
- You need subtitles for a video.
- A podcast episode needs a searchable transcript.
- Product names keep getting misspelled in your transcripts.
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 use your own ElevenLabs API key.