Hire an AI recording transcript and clip planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A clean speech file with the noise and music removed
• A timed transcript with who spoke, ready for subtitles
• A cut list with timecodes for dead air, fillers and retakes, and the time saved
• A chapter list that starts at 00:00 and follows YouTube's rules
• Up to five short clips, each with a new first line, on-screen text and a loop point

How it does the job well

• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.
• Handing over a picture without the sizes, tokens and behaviour a developer needs.

What a good result looks like

An example, not your task: You recorded a talk, podcast, lesson or interview and it needs tightening.

• Clean audio. Your speech with background noise and music removed, plus a note of what was made.
• Timed transcript. Every word with timing and who spoke, ready to use as subtitles.
• Cut list. Each pause, filler and retake with a timecode, and the total time saved.
• Chapters. A chapter list starting at 00:00 that follows YouTube's rules, with short promise-style titles.
• Short clips. Five ranked clips with timecodes, a new first line, on-screen text and a loop point.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order. Steps 4 and 5 used the step 2 transcript, not the step 3 cut list.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Clean the sound. Sends the recording to ElevenLabs voice isolation, which removes background noise and music. You listen to the result before you rely on it.
• Write a timed transcript. Transcribes the clean file, labels who spoke and keeps timing for each word.
• List the cuts. Finds gaps longer than the pause you set, filler lines and restarted sentences. Lists each cut with a timecode and the time saved.
• Write the chapters. Finds section breaks from pauses and topic shifts in the step 2 transcript, checks the list meets YouTube's rules and retitles each chapter as a short promise. If you publish the cut version, move each time by the cuts.
• Find the clips. Picks spans of 20 to 55 seconds that open on a full thought and end on a line. Ranks up to five and writes a new first line for each. It reads the step 2 transcript, so check each clip's times against the cuts.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id cut-a-raw-recording-and-get-chapters-and-short-clips only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/cut-a-raw-recording-and-get-chapters-and-short-clips/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The raw recording, as an audio or video file
• An ElevenLabs account and key for cleaning and transcribing. ElevenLabs is paid, and the run stops at step 1 without a key.
• The length of pause you want cut (optional)
• Your channel's tone (optional)

Tools and access

• Claude, ChatGPT or Gemini: Any chat AI works. Paste the transcript in. No code runs.

Functions and deliverables

• Recording transcript and clip planner: Clean up recording audio, make a timed transcript and get a cut list, chapters and five short-clip candidates.
  • A clean speech file with the noise and music removed
  • A timed transcript with who spoke, ready for subtitles
  • A cut list with timecodes for dead air, fillers and retakes, and the time saved
  • A chapter list that starts at 00:00 and follows YouTube's rules
  • Up to five short clips, each with a new first line, on-screen text and a loop point
• Noisy audio cleaner: Use ElevenLabs Voice Isolator to cut noise. Get speech audio from a file or link.
  • A clean speech audio file
  • Code to run it on more files
  • A faster PCM option for low delay
  Source: ElevenLabs.
• Subtitle and transcript maker: Turn a meeting, interview or video into a written transcript with who said what and the time of each word. Uses ElevenLabs speech to text and your own API key.
  • A full text transcript
  • Speaker labels
  • Word-level timestamps
  • Word timing you can turn into a subtitle file
  • A request ID to track usage
  Source: ElevenLabs.
• Dead air and retake cutter: Give it your recording transcript. Get a timed list of pauses, fillers and retakes to cut.
  • Timed cut list
  • Labels for dead air, filler and repeats
  • Estimated time saved
  • JSON version for tools (optional)
  Source: Jake Schincariol.
• YouTube chapter writer: Turn an SRT transcript into a chapter list with short titles and timestamp rule checks.
  • A valid chapter list starting at 00:00
  • A rule check that it will work on YouTube
  • Rewritten five-word chapter titles
  • A flag on any section that is two sections or filler
  Source: Jake Schincariol.
• Shorts clip finder: Share a long video transcript. Get the best five moments to clip, each with a new first line.
  • Five ranked clip moments with start and end timecodes
  • A new first line for each clip
  • On-screen text for the first two seconds
  • A loop point for each clip
  • A crop note for vertical video
  Source: Jake Schincariol.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one

Tasks you can use it for

• You recorded a talk, podcast, lesson or interview and it needs tightening.
• The room was noisy and you need clear speech first.
• You want chapters and short clips out of one long recording.

Limits to check before starting

• You only need subtitles for a clean recording: use the Subtitle and transcript maker on its own.
• You want to make video ads: use the Video ad shot list maker.
• You want the cuts applied for you: this gives a cut list, so a video editor or a person must make the cuts.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Point it at your recording and set up your ElevenLabs key when asked.
• Listen to the cleaned file when step 1 is done. If the voice sounds damaged, use the original and start at step 2.
• Apply the cut list in your editor and publish the chapters and clips yourself.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/cut-a-raw-recording-and-get-chapters-and-short-clips for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.