YouTube Voice Actor

NARRATOR — YouTube commentary channels (SML Universe, Gumball Universe, + others)

Ongoing paid work. ~15–30 min of finished narration per video, multiple videos/month.

── PLEASE READ: AI IS INVOLVED, AND WE'RE UPFRONT ABOUT IT ──

Your recorded performance is processed through a voice model so the final

audio matches our channel owner's voice. To be completely clear about what

that means:

• We are NOT buying your voice, and your voice is never published.

• Your PERFORMANCE is the product — your timing, pacing, emphasis and

energy all pass through completely unchanged. That's the entire reason

we're hiring a human instead of using text-to-speech.

• You are paid per session, at above-standard rates because of this.

• A written agreement covers scope and duration before any paid work.

• You keep full credit as the performer in our internal records.

If that's not something you want to be part of, no hard feelings — please

skip this one rather than audition.

── WHAT WE ACTUALLY NEED ──

We are casting for RHYTHM, not for voice. The model handles tone. What it

cannot do is decide where to punch a word or when to speed up, so that's

the whole job.

The channel voice is: a knowledgeable superfan talking fast and casually to

other fans. Energetic, opinionated, slightly unhinged. NOT calm, NOT a

documentary narrator, NOT "video essayist."

Specifics:

• Long, flowing sentences — often 40+ words chained with commas. You must

sustain energy across a whole sentence without flattening out.

• 1–3 CAPS words per sentence get real spoken stress. Hit them hard.

• Dramatic pauses and trailing ellipses to end a beat.

• Fast delivery. Conversational, not polished-announcer.

Vocal requirements:

• Male, native American accent

• Natural speaking pitch roughly 140–180 Hz (we measure this from your

audition — don't worry about the number, just send natural speech)

• WIDE pitch range. A flat or monotone read will not work, even a

technically perfect one.

── RECORDING REQUIREMENTS ──

• Decent condenser or dynamic mic, treated/quiet room

• 48kHz WAV, mono

• COMPLETELY DRY — no compression, EQ, noise gate, de-esser or reverb.

Processing on the way in makes our conversion worse, not better.

• Consistent mic distance

── EXAMPLES OF THE CHANNEL VOICE ──

Watch 2–3 minutes of any of these before auditioning:

https://www.youtube.com/@ItsSMLUniverseYT
https://www.youtube.com/@ItsGumballsUniverse

── HOW WE PICK ──

If you REALLY can nail exactly how the narrator voices these videos, and you can replicate that really well, along with being okay with the use of AI, that is exactly what I'm looking for.