# VoiceStudio

> Voice cloning and dubbing on your PC — Clones voices, dubs video and transcribes audio on your own machine.

- Page: https://tesign.com/en/item/voicestudio/
- JSON: https://tesign.com/en/item/voicestudio/index.json
- Korean Markdown: https://tesign.com/item/voicestudio/index.md
- Generated: 2026-09-17 01:56 UTC

## RANKS

- All-time #238 · Rising this week #4 · MEDIA #5 (As of 2026-09-16 21:00 UTC)

## Numbers

- 30,862 stars — checked on GitHub 2026-09-15 19:33 UTC (+163 observed since the check)
- 7-day +1,260 observed via GH Archive (as of 2026-09-16 21:00 UTC)
- 24h +144 ★ · 30d +2,607 ★ (as of 2026-09-16 21:00 UTC)
- Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours.

## AT A GLANCE

- LICENSE: AGPL-3.0 (copyleft) — https://spdx.org/licenses/AGPL-3.0.html
- USAGE: Release source if you redistribute or host it as a service.
- OPEN SOURCE: YES
- LANGUAGE: Python
- PLATFORM: macos · windows · linux
- CATEGORY: AI · MEDIA
- Tags: voice · local-models · audio
- How to start: Self-host
- SOURCES: GitHub https://github.com/debpalash/voicestudio
- SELF-HOST: https://voicestudio.sh/

## ACTIVITY

- Last commit: 2026-09-15 14:32 UTC
- Latest release: v0.5.2 (2026-09-10)
- Contributors: 56
- Open issues (incl. PRs): 99
- Made by: an individual
- Checked on GitHub: 2026-09-15 19:33 UTC

## Signals and evidence

- RISING · +144 ★ / 24h

## TESIGN TAKE

If you want voice cloning, dubbing and dictation without sending audio to a service, start here.

## WHY IT MATTERS

Working with voice usually starts by uploading the original recording to somebody else's service. voicestudio keeps cloning, dubbing, dictation, transcription and audiobook production on the machine in front of you, so the audio never leaves it. The repository states coverage of 646 languages; it is written in Python and published under AGPL-3.0. It is self-hosted, so the runtime environment is yours to prepare.

## BUILD FROM THIS

- A dubbing workflow that stays in-house with no external upload
- An internal tool that transcribes meeting recordings
- An audiobook line that reads your scripts in a brand voice

## WHO IT'S FOR

- Video maker — dubs and transcribes without uploading audio elsewhere
- Solo business — needs voice prompts or audiobooks made in-house
- Developer — wants a local, OpenAI-compatible speech API

## START IN 5 MINUTES

```
# Download the macOS DMG, Windows MSI or Linux AppImage from Releases
# First launch fetches a Python env and the default model. From source:
$ git clone https://github.com/debpalash/VoiceStudio.git
$ cd VoiceStudio
$ bun install
$ bun run desktop
```

## CAVEATS

- Active beta; the desktop app is being rewritten on Electron
- Default model weights are CC-BY-NC: check model terms before commercial use
- Intel Macs cannot run the local backend; a remote backend is required

## RECEIPT

- FIRST SEEN BY TESIGN: 2026-09-13 07:43 UTC
- AT SOURCE: 2026-04-09 21:40 UTC
- KEPT: 2026-09-13 11:32 UTC
- Published on TESIGN: 2026-09-13 11:32 UTC
- Text last updated: 2026-09-15 04:36 UTC

## How to read this

- This file was produced by the same build, from the same data, as the tesign.com item page. The text is editorial; the numbers are stored observations.
- null in the JSON means not observed — never zero. The Markdown writes [unconfirmed] for it.
- Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours.
- A summary, not legal advice.

[Image] https://tesign.com/img/voicestudio-745990c230.png