- Pipeline
Transcribe → translate → re-voice
- Speakers
Each speaker kept and re-cast
- Local API
POST /dub/upload on localhost:3900
Drive it from the Local API
The desktop app exposes an OpenAI-compatible API on localhost.
On your machine · port 3900
Local API
http://localhost:3900/v1- POST
/v1/audio/speechText to speech - GET
/v1/audio/voicesList voices - POST
/v1/audio/transcriptionsSpeech to text - POST
/dub/uploadDub a video
quickstart.tsOpenAI-compatible
import OpenAI from "openai";const client = new OpenAI({ baseURL: "http://localhost:3900/v1", apiKey: "local",});await client.audio.speech.create({ model: "tts-1", voice: "alloy", input: "VoiceStudio is ready.",});Free · open source · AGPL-3.0
Download VoiceStudio
fully-local voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages
DownloadmacOS · Windows · Linux · Docker