Skip to content
decosa
decosa
Get an API keyTry a tool

Industries

LegalBriefs, depositions, discovery, records, client calls.HealthcareThe visit, then notes, audits and denials.Finance & insuranceAlerts, SARs, disputes, claims, recorded calls.HRInvestigations, leave and I-9 audits.Compliance & trustSecurity questionnaires, control evidence, AI audits.OperationsForms, shop pages, imports, listings: any industry.Life sciencesTrial numbers, safety cases, labels, papers.

More industries

Public sector 2 toolsSales and marketing 6 toolsScience and research 6 toolsMusic 5 toolsFilm, TV and games 6 toolsAll industries

Create and tools

CreateTools

Developers

Decosa APIQuickstartAPI referenceAPI pricingBuilding blocksDecosa agentAssembly promptsFor AI agentsSelf-hosting docsVerify a runAccuracyStatus

Trust

Where your data goesHosted APISelf-hostOn a MacConfidential optionDecosa for ChromeAccuracyVerify a runStatusSecurityRegulation watchCompare ways to run it

Company

PricingAboutApps by DecosaContact

VoiceLive

Your words performed: in your own voice, or by a consented cast.

Dub your video into Spanish in your own voice, after you record your consent. Or paste a radio script or a chapter and produce an audio drama with consented house voices, sound cues and music.

Make an audio drama Your projects

Works on its own today. Reading your project's cast is next.

Chapter one of a narrated story, voiced by consented house voices.

Tools in Voice

  • Dub a video in your own voice

    Live

    A Spanish track for a creator's video in the creator's own consented voice, or in a consented dubber's.

    Try it Details

  • Produce an audio drama

    Live

    Paste a radio script or a prose chapter and review the parse: every speaker, line, direction and sound cue, before anything is voiced.

    Try it Details

Coming to Voice

  • Read a chapter in your own voice
  • Make a podcast episode
  • Invite a grandparent to add their voice
The rules
  • Every voice passes the consent ledger before it's rendered, and again before it's delivered.
  • Cloned voices carry a watermark and a credential.
  • Every file carries a C2PA content credential and a signed render receipt.
Models and licences

Chatterbox Multilingual (MIT, voice clone), Kokoro (house voices), Qwen3.8-27B (script parsing)

Each tool's page lists every model with its licence, the hardware it needs and how to run it yourself.

Accuracy, time and cost per run: Dub a video in your own voice · Produce an audio drama

Use it through the API

Each tool has its own API with dk_ keys. Open a tool's Details page for its routes, a self-host recipe and a prompt you can give a coding agent.