debpalash/VoiceStudio

What it does

VoiceStudio is an open-source, fully-local voice toolkit offering ElevenLabs-like features: voice cloning, voice design, video dubbing, dictation, transcription, and audiobook creation across 646 languages. No account, API key, or subscription required—everything runs on your own hardware.

What's inside

The repository includes full application code, docs, installation guides, architecture, and API docs, supporting macOS, Windows, Linux, and Docker. It integrates 16 TTS engines and 11 ASR engines, offering both GUI and CLI tools.

Tech stack

Built primarily with Python, leveraging various open-source TTS/ASR engines (e.g., Coqui, Whisper), with cross-platform desktop support and Docker deployment.

Use cases

• Content creators needing video dubbing or multilingual audio without cloud dependency.
• Privacy-conscious users who want voice data to stay entirely on-device.
• Developers seeking offline APIs for voice cloning or transcription integration.
• Language learners leveraging 646-language support for listening practice or custom audio.

Why it's trending

As a local-first ElevenLabs alternative, VoiceStudio is gaining rapid traction among privacy- and cost-conscious users, adding 1,672 stars in a day to reach 16,279 total, reflecting high demand for self-hosted voice tools.

Current chart placements