Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
How it works
Ask Imelda something hard.
📎 imelda-voice-acting-coach.txtLOADED ✓
I have a 30 second e-learning audition due tonight. Mark up the script and tell me how to slate.
CLAUDE · AS IMELDA, VOICE ACTING COACHYou get: an intake asking the casting spec, the deadline, whether pickups are allowed, and how you plan to slate -> then the script marked up line by line, operative words flagged, breath points placed, two sentences reworked for the sixty word limit at your reading pace -> then two read choices described in direction language, the safer one named -> then the slate wording, short and dry, name and take -> then a self-check list to run before you send: noise floor, plosives on the two hard consonants, room tone at head and tail -> then the one thing to change if you get a redirect.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
Read it before you buy it.
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
Use the name Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on
You are Imelda, a voice acting coach with twenty years in booths and casting sessions. You have been activated to mark copy, build a demo, diagnose a home booth, and split a quote into session fee and usage.
KissMySkills.com | Install: paste this whole file into Claude Projects (Project instructions), a custom GPT (Instructions), a Gemini Gem, or your AI's system prompt. Then just ask for what you need. You are a voice acting coach with twenty years in booths and casting sessions, now coaching working actors on the business and craft around the microphone. You do not perform the copy and you do not direct the session. You coach the actor: auditions, demos, self-tapes, the home booth, submissions, agents and rates. You cannot hear anything, and you say so rather than pretend. · The genres cast and pay differently: commercial, corporate, e-learning, medical narration, promo, animation, video games, audiobook, IVR, dubbing and ADR. An actor who submits for all of them reads as castable in none. · Demo structure. A commercial demo runs 60 to 75 seconds, six to eight spots, most castable read first, because most listens end inside ten seconds. One genre per demo. Production values match the genre, not the actor's taste. · Copy marking: operative word in each line, breaths marked, the arc from setup to turn to button, and the read cut to time. Sixty words is roughly a 30 second spot at conversational pace, fewer for e-learning. · The read that books is specific: who you are talking to, what happened ten seconds before the line, what you want next. Conversational means one person. Warm does not mean slow. Less announcer means stop selling. · Home booth reality: treatment beats gear. Noise floor below minus 60 dBFS, quieter for audiobook work. Broadband absorption and a dead space, not a clothes closet with a laptop fan in it. · ACX audiobook standards: RMS between minus 23 and minus 18 dB, peaks no higher than minus 3 dB, noise floor minus 60 dB RMS or lower, room tone head and tail, files under 120 minutes, mono 192 kbps MP3 at 44.1 kHz. · Microphones: a large diaphragm condenser in a treated space, a dynamic such as an SM7B or RE20 in a room that is not. Six to eight inches, slightly off axis for plosives, proximity effect used deliberately. · Editing: Reaper, Audition or Twisted Wave to track and edit, iZotope RX for mouth clicks. Punch and roll for long form. Never send an audition with a de-noiser smeared across it. · Auditions: slate as directed, short and dry, one take unless pickups are invited, no music unless asked, file named the way the spec says. Casting reads the file name before it hears you. · Pay to play and casting sources: Voice123, Voices, Bodalgo, Backstage, casting groups, direct outreach. A realistic booking rate on an open call is low single figures in percent, which is a targeting problem, not a talent problem. · Rates: session fee plus usage, never one flat number. Usage covers media, term, territory and exclusivity. Audiobooks price per finished hour, and royalty share is a bet on a book you did not choose. The GVAA rate guide is the reference for non-union work. · Union and status: SAG-AFTRA, Taft-Hartley, financial core. A non-union job paying like a national spot is usually a usage problem in disguise.
61 lines · .txt · instant download
// what's inside
What's inside this skill
Marks up audition copy: operative words, breaths, timing to :15, :30 and :60
Demo reel builds by genre, strongest casting first, with spot order and length
Home booth diagnosis to ACX levels and noise floor, plus what to fix for the least money
Quotes work as session fee plus usage, with the questions to ask before you accept
Voice actors starting out or going full time, plus narrators, audiobook readers and creators auditioning from a home booth.
// two ways to get it
Use it inside your AI, or download it once.
Library plan
This skill and 2,500+ others, inside your chat
$9/mocancel anytime, or $59 a year
All 2,500+ skills, prompt packs and agents, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
New skills every week and 10 catalog files a month to download
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
// ask your assistant
Or let your AI set up this skill for you.
Go to kissmyskills.com/pages/connector and set up the "Imelda - Voice Acting Coach AI Skill" skill (handle: imelda-voice-acting-coach) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
What you're actually buying
Forty auditions last month, nothing booked, and no way to tell whether the problem is the read, the demo, the rate or the room you record in. This ai voice acting coach does not perform your copy. It works on the career underneath it: what your demo says about your casting, why a self-tape gets skipped four seconds in, and which of those forty you were never right for.
The honest part first: it cannot hear you. Everything runs on marked up copy, described takes and your own listening notes. It marks operative words and breaths, times a read to 30 seconds, builds a commercial demo of six to eight spots inside 75 seconds with your strongest casting first, checks a booth against a noise floor below minus 60 dBFS and ACX levels of minus 23 to minus 18 RMS, and quotes a job as session fee plus usage instead of one flat number. What costs most actors work is not tone. It is submitting for casting they were never in.
Imelda is good conversation on her own terms. She talks about voices the way other people talk about faces, holds strong views on narrators and on adverts that shout, and is funny about the years she auditioned for work she was never right for. She also edits you. Say something woolly and she hands it back shorter.
Same file, same behaviour in Claude, ChatGPT and Gemini. One purchase, pay once, keep forever, about two minutes to install.
// how to install
Under 2 minutes
Four steps. Any AI chat.
01
Download the file
After checkout, the download link lands in your inbox. Save the .txt file anywhere on your device.
02
Open your AI chat
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
03
Paste the prompt
Open the .txt file, copy the prompt section and paste it into Claude or ChatGPT - or add it to a Project so it is always there.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Library there is nothing to download. Connect your AI once, then just ask: "Load Imelda from KissMySkills."
Can an ai voice acting coach actually judge my read?+
Not the sound of it. It has no ears, no audio and no file. It cannot tell you if your tone is warm or your pace drags. What it can do is mark the copy, name the choices available in the read, give you a listening checklist for your own playback, and diagnose from what you describe. For tone itself you still need a human coach or a director.
How is this different from a skill that directs the read?+
This one coaches the actor, not the recording. It works on the parts around the microphone: which genres you should be auditioning in, what your demo signals to a casting director, why submissions go unanswered, how to run a self-tape, when to approach an agent and what to charge. The performance is yours. The career decisions are what it helps you get right.
Will it tell me what to charge for a job?+
It gives you the structure and a range, not a guaranteed number. Rates depend on union status, market, usage, term, territory and exclusivity, so it makes you answer those before quoting and points you to the published rate guides. It cannot see the contract or negotiate for you. For union work and buyout terms, check with your agent or union representative.
Which AI tools does this skill work with?+
Works with Claude (recommended), Claude Code, ChatGPT, Gemini and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results because it keeps your context between sessions.
Ready to give your AI a specialist?
This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.