VoiceStudio

aimediaprivacy

Local voice production suite for cloning, speech generation, transcription, dubbing and audiobooks, with desktop applications, Docker deployment and an OpenAI compatible API

#ai#voice-cloning#text-to-speech#transcription#dubbing#audiobooks#local-ai#self-hosted
Alternative to ElevenLabsDescript

Quick Start

docker compose up -d

Overview

VoiceStudio is a local voice production suite for cloning voices, generating speech, transcribing recordings, dubbing video and producing audiobooks. It runs on Windows, macOS and Linux, with Docker deployment available for server workflows. Mobile applications are also under active development.

You can start with the bundled OmniVoice engine or install another supported speech engine. Language coverage, cloning quality and hardware requirements depend on that choice, so the advertised language total should not be treated as equal support across every workflow. Audio stays on your hardware by default, while remote services are optional and usage analytics requires consent.

VoiceStudio also provides a local OpenAI compatible API and an MCP server for connecting coding agents and other applications. The API listens on localhost without authentication by default. You should configure an API key, TLS and network restrictions before exposing it beyond the machine.

The application source uses AGPLv3, but downloaded models retain their own licences. The default OmniVoice pretrained model permits noncommercial use only, and purchasing future Pro features will not override model restrictions.

The open source edition is free. A paid Pro edition and hosted Cloud service are planned, but the Cloud API remains a preview rather than a currently available hosted product.

VoiceStudio: Pros & Cons

Pros (The Wins)Cons (The Friction)
Local processing:
Audio can remain on your machine.
Remote services are optional.
Model licences:
Terms vary by engine.
OmniVoice is noncommercial.
Deployment choices:
Desktop and Docker options.
Local API and MCP included.
Resource use:
Models need storage.
Inference speed varies.
Broad workflow:
Cloning, dubbing and books.
Transcription is included.
Remote access:
API security must be configured
before network exposure.

Use Cases

Specific ways to use VoiceStudio for your workflow.

01
Clone an authorised voice sample and generate speech without uploading the recording
02
Transcribe recordings and create subtitles on local hardware
03
Dub video while retaining timing and speaker characteristics
04
Produce long form narration and audiobooks through repeatable workflows

Deployment Strategy

Recommended ways to host VoiceStudio in your own environment.

docker
desktop
mobile
self-hosted