VoiceStudio
VoiceStudio is a fully-local, open-source ElevenLabs alternative for voice cloning, dubbing, dictation, and transcription in 646 languages.
Overview
VoiceStudio (github.com/debpalash/VoiceStudio), an AGPL-3.0-licensed desktop app first published April 9, 2026, became the highest-velocity AI project on GitHub in late September 2026, gaining roughly 4,750 stars in 24 hours and crossing 50,000 stars by September 29-30 as developers adopted it as a fully-local alternative to ElevenLabs. The app runs entirely on-device with no API keys, accounts, or cloud dependencies, bundling 16 text-to-speech engines and 11 speech-recognition engines for voice cloning, voice design, video dubbing, real-time dictation, transcription, and audiobook creation across 646 languages, with support for macOS, Windows, Linux, and Docker across CUDA, Apple Silicon MPS/MLX, ROCm, CPU, and optional remote-worker compute backends.
This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.
Key features
- Fully local execution -- no API keys, accounts, or cloud dependencies
- 16 bundled TTS engines and 11 ASR engines
- Voice cloning, voice design, video dubbing, dictation, transcription, and audiobook creation in 646 languages
- Cross-platform (macOS, Windows, Linux, Docker) with CUDA, Apple MPS/MLX, ROCm, and CPU backends
- AGPL-3.0 licensed, over 50,000 GitHub stars as of September 30, 2026
Use cases
- Running voice cloning and dubbing entirely offline for privacy-sensitive content
- Self-hosted alternative to commercial voice-AI APIs like ElevenLabs
- Audiobook and multilingual dubbing production across 646 languages
Pricing
free and open-source (AGPL-3.0); self-hosted, no paid tier
Pricing reflects the source record and may change. Confirm current terms with the provider.
Dates and sources
- Released
- Not listed
- Record updated
- 1 Oct 2026
- Record last checked
- 1 Oct 2026