
Content · The Scoring Stage
Every sound your brand makes. Mastered and cleared.
Voiceovers, podcasts, music, songs, phone greetings, sound effects and audiograms. Free by default, broadcast volume. Voice cloning needs a signed release.
demo businessWhat it is
The audio studio most businesses never had
The Scoring Stage makes audio: voiceover, podcast, music, phone greeting, sound effect or audiogram (a waveform video for social). Write or let your assistant draft the script, pick a voice, generate. Free, at the right volume.
Bad audio ruins good video, and few owners know “−16 LUFS”. The studio masters each take for its platform, ducks music under voice, and shows the real loudness reading.
Voice cloning isn't offered yet. When it is, a signed release comes first.
Walk it
From script to sound in 6 steps
- 01
Pick what you're making
Voiceover, podcast, music, phone greeting, sound effect or audiogram.
example data - 02
Your script Your assistant
Write it, or let your assistant draft it in your brand voice.
- 03
Choose a voice You
Any stock voice, or record a quick consent and clone your own.
- 04
See the shape
A preview shows the shape of your audio before you make the real take.
- 05
Make it Free
Generate. Free by default, set to broadcast volume for you.
- 06
Send it on
To the Finishing Bay to sit under B-roll, or straight to the Screening Room.
Everything included
Everything in the Scoring Stage
Outcomes
- Voiceover
- Podcast
- Music
- Phone tree (IVR + on-hold)
- Sound effects
- Audiogram
Voices
- Willa Warm
- Reed Announcer
- Poppy Local
- Owner voice (needs a release)
- Series host (needs a release)
Music
- Genres: cinematic, lo-fi, corporate, ambient, acoustic, hip-hop, rock, EDM
- Moods: uplifting, tense, warm, epic, chill, playful
- Lengths: 15 seconds to 2 minutes
Controls
- Languages: English (US), English (UK), Spanish (US), French
- Speed 0.75× to 1.5×
- De-noise, de-ess, high-pass, low-pass, limiter
- Pause and emphasis marks
- Hook · Value · Proof · CTA block markers
Export
- WAV
- MP3
- M4A
- Opus
The rules it follows
- Phone tree: Telephony-mastered at 8 kHz; a TCPA note rides with every prompt.
- Clone a voice: A signed release is required before any synthesis. Withdraw consent and it stops.
- Keep it one voice: Settings saved per voice, so a whole series sounds the same.
The engines behind it
- Kokoro-82M (planned): Fast, clean narration, the free floor (free engine, $0)
- Piper (planned): Telephony voice at 8 kHz (local, $0)
- See every engine in this group
Who runs it
YOUR TEAM with the OS, or OUR TEAM for you.
- Pick the outcome and approve the script
- Record consent to clone your voice
- Approve before it ships
- Drafts, voices and masters every take
- Tracks rights and credits
- Blocks any clone without a release
- Audio creation for videos and ads
- AI voice cloning, consent built in
- Phone greetings and on-hold messages
Built and free by default. Premium voices and sung songs need a key and ask first. Phone greetings go live once your phone line is connected. Stock synthetic voices carry the FTC disclosure.
On the way
Coming soon
These are planned and are not in the software yet. We list them so you know what is next.
A live waveform and quick voice previews.
Coming soon: V2Make audio in your own voice after you sign a release.
Coming soon: V2Keep going
Related pages
Try the OS
Our free trial is starting soon.
The same tools we use for our done-for-you clients. Our 7-day free trial is starting soon. Until then, book a call and a real person walks you through the OS. $997 a month, first month $497. No contracts.

YOUR TEAM runs it with the OS, or OUR TEAM runs it for you with Done-For-You. Not sure? Which one fits me?





