Voice recording for TTS and voice AI. One voice, cast, directed and licensed in writing.

YPAI casts the voice, directs the sessions and writes the rights down before the first take. The model learns from recordings that carry the performance you specified and the permissions you need.

Scope a voice recording

Example session

First take Pickup Reviewed Accepted take

Anyone can record a voice. The rights decide what you can build.

A TTS, cloning or assistant voice needs more than a clean file. It needs to carry:

A voice file

a recording in a file format

A contracted voice

who the voice is, chosen against the brief
the pronunciation reference it was checked against
the register, pace and emotion that were directed
the room, microphone and format held constant
every take, logged and reviewed
the script it was written for
the talent's documented consent to the use
the training and evaluation rights
the cloning, exclusivity and resale grants
the term and territory the grants run for

YPAI delivers these as one record around the voice, with the licence written before the session.

The same holds when the voice already exists: a recording becomes usable for a model when its casting, session and rights can be shown in writing. If the gap is coverage across speakers and conditions, that is a managed collection, on its own route.

The project is built around the use the voice must serve.

That use may be:

a product voice for a TTS system
a cloned voice, with the talent's documented consent
an assistant persona across languages
narration for long-form content
a brand voice under exclusivity

The casting, session plan, take log and licence schedule follow that use.

Start with the voice you need.

YPAI can run one defined stage or the whole recording programme.

Entry point: Cast and record a new voice

Start here when: You need one voice that your data does not contain.

Typical output Recorded voice files, directed take by take, with the take log and the licence schedule.
Entry point: Extend a voice you already use

Start here when: A model needs more of an existing voice: pickups, new registers, new scripts.

Typical output Additional sessions in the same chain, logged against the original record.
Entry point: Collect a population instead

Start here when: The gap is coverage across speakers and conditions.

Typical output A managed collection against agreed speakers, conditions and checks, on its own route.

A director from behind wearing headphones, reading a fanned stack of candidate sheets beside a laptop with a soft waveform glow

The casting brief fixes language, accent, register, age range and the pronunciation reference. Candidates record the same passage under the same conditions, and the choice is made on those takes.

Brief → same passage, same conditions → one chosen

The chosen voice's consent to the intended use is documented before production.

Example licence schedule

Permitted use: model training
fine-tuning
evaluation
regression sets
inference
internal testing
derivative models
permitted products
Voice identity: voice cloning
documented consent to cloning
likeness
name and attribution
synthetic re-use
style transfer
Commercial scope: buyout
exclusivity
resale
sublicensing
distribution
white-label
end-client disclosure
reseller terms
Term and territory: term
territory
renewal
termination
post-term use
archive
Session record: casting brief
pronunciation reference
script version
take log
reviewer decision
delivered files
format
Provenance and indemnity: consent record
rights status
indemnity
deletion right
audit trail
signed schedule
schedule version

The licence schedule is signed before the first take.

Voice-cloning, buyout, exclusivity, resale, sublicensing, distribution and white-label rights need an explicit written grant.

A sound engineer from behind at the console, a condenser microphone and pop filter in front, the voice talent visible through the glass.

A vocal booth with a condenser microphone on a boom arm, a pop filter, and a script on a music stand. — Script and pronunciation reference

A condenser microphone with a reflection filter, headphones and a lamp on a desk. — One chain, held constant

Register, pace and emotion,
directed take by take.

A director holds register, pace and emotion constant across takes, and pickups are recorded in the same chain.

A vocal booth, condenser microphone and script stand under one lamp.

Brief
Casting
Direction
Takes
Review

Take / logged with script line and numberReview / reviewer decision recordedPickup / same chain, same day where the schedule allowsAccepted / named and delivered

The session plan is built against the customer's script, use and pronunciation reference.

Studio-clean is one condition.
The brief sets the others.

Train a voice for a car, a call centre or a kitchen and the booth is the wrong room. Conditions are set per brief; microphone and format are held constant inside each.

A condenser microphone with a reflection filter on an office desk at night, headphones, a laptop and blinds behind.

Booth
Office
Vehicle
Home
Street
Café

The room is part of the brief; the microphone and the format stay fixed inside it.

A fountain pen resting on the signature line of a signed voice rights agreement. — Ships with the signed schedule

Delivery is defined before the session, not after.

Every take is accepted or sent back before the files are named and delivered.

AcceptedPickupRe-recordedReplacedRejected

Files are delivered as WAV or FLAC at 48 kHz with the take log, the script alignment and the licence schedule. Noise floor, naming and transfer follow the technical specification agreed for the project.

Ships with the accepted takes / take log · script alignment · pronunciation reference · session record · consent record · licence schedule · checksums

Delivered as WAV or FLAC, or mapped to the customer's TTS training layout. Format support is checked against the actual toolchain and delivery requirement.

Different voices need different sessions. TTS product voice · cloned voice with documented consent · assistant persona · narration · brand voice under exclusivity. Cast from contributors in 150+ languages.

Which rights go into the licence schedule?

The schedule is defined for your use, model and territory. It can grant model training, fine-tuning and evaluation, voice cloning with the talent's documented consent, buyout, exclusivity, resale and sublicensing, and it sets the term and territory. It is signed before the first take.

How is the voice chosen?

The casting brief fixes language, accent, register, age range and the pronunciation reference. Candidates record the same passage under the same conditions, and the voice is chosen on those takes. The chosen voice's consent to the intended use is documented before production.

Can sessions be recorded outside a studio?

Yes. The brief sets the room: booth, office, vehicle, home, street or café. The microphone and the format are held constant inside each condition.

What is delivered with the recordings?

WAV or FLAC at 48 kHz, or files mapped to your TTS training layout, with the take log, script alignment, pronunciation reference, session record, consent record, licence schedule and checksums. Noise floor, naming and transfer follow the technical specification agreed for the project.

Can you extend a voice we already use?

Yes. Pickups, new registers and new scripts are recorded in the same chain and logged against the original record. When the gap is coverage across many speakers and conditions, the project is a managed collection instead.

Which languages can you cast in?

Voices are cast from contributors in 150+ languages.

Send the script, the voice brief and the rights you need.

The use, the language and register, the script, the conditions, the rights and the delivery format. YPAI returns the casting plan, the session plan and the licence schedule to sign off before the first take.

Scope a voice recording Scope the licence schedule

Voice recording for TTS and voice AI. One voice, cast, directed and licensed in writing.