VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languages
In today's Spotlight · Picked by 3 of 3 modelsClone voices, dub videos, and transcribe in 646 languages entirely on your own machine.Like a recording studio that fits in your laptop and needs no internet.
VoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video dubbing, dictation, transcription and audiobook creation in 646 languages. Ships via Docker with an official Google Colab notebook for zero-install use.
Why it matters
Trending #1 on GitHub today with 49k stars: it shows local voice cloning and multilingual dubbing matching commercial quality without sending a byte of audio to a cloud API.
What you could build with it
A media or education startup can run privacy-safe voice cloning and multilingual video dubbing on its own servers, generating localized audiobooks or course narration in dozens of languages with no per-minute API cost.
Does it hold up?
Battle-tested: 49k stars and today's #1 GitHub trending repo; the README ships listenable sample outputs for cloning, voice design and ES/FR/JA/ZH dubbing so quality can be judged before installing.
Built with VoiceStudio
- Try VoiceStudio without installing: official Google Colab notebookgithub · The project's Colab notebook runs the full studio (cloning, design, dubbing) in the cloud with no local install.
Learn more
First spotted on github: source.
More AI models
ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69Mistral Forge: enterprise platform for training and continuously improving proprietary modelsMistral AI launched Forge (Sep 28) — a full-lifecycle model training platform (pre-training, SFT, DPO/ODPO, RL…models · JEV 0.69kev: open, trainable Jev-like family of small decision models on Qwen3.5/3.8A family of small decision models (0.8B to 27B) built on Qwen3.5/3.8 that reproduces Jev's prefill-only typed-decision…models · JEV 0.68GPT-Synopsys: OpenAI and Synopsys multi-year deal to build an AI model that operates EDA toolsOpenAI and Synopsys signed a multi-year agreement on Sep 30 to jointly develop GPT-Synopsys, a specialized model that…models · JEV 0.66Claude Sonnet 5.5: 30% faster, up to 30% cheaper per taskAnthropic's new mid-tier: 70.6% on Terminal-Bench 4.0 (vs 10.3% for Sonnet 5), 46.2% FrontierCode 1.1 max-effort…models · JEV 0.65
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.