VoiceStudio: the open-source, fully-local ElevenLabs alternative
A desktop app bundling 20 local speech-generation engines and 10 transcription options behind one UI — voice cloning, voice design, video dubbing, dictation and audiobook production in 646 languages, with no account or API key.
Why it matters
Everything runs on your own hardware: zero-shot voice cloning from a few seconds of audio, plus an OpenAI-compatible local API and MCP server so agents can call the same voices.
What you could build with it
An indie podcaster could run VoiceStudio on their own machine to clone a consistent narrator voice, dub episodes into other languages, and generate audiobook chapters — without sending voice data to a cloud service or paying per-character fees.
Does it hold up?
Usable today as a local voice workstation — reviewers note the Electron app runs fully offline with an OpenAI-compatible local API; the caveats are the AGPL app licence, CC-BY-NC default model weights, and multi-gigabyte model downloads.
Built with VoiceStudio
- VoiceStudio: Free Local ElevenLabs Alternative, 16 TTS Enginesexplainx · How the engine-swapping model works: 16 TTS and 11 ASR engines, selected per job, with a Colab notebook to try it first.
- VoiceStudio: The 82k-Star Open-Source ElevenLabs Alternative That Runs Fully Localdev.to · Deep dive on the multi-engine orchestration layer, the four project modes, and the local API and MCP for agents.
- VoiceStudio is a free, fully localized ElevenLabs alternativegigazine · GIGAZINE's Nov 1 walkthrough: voice cloning, voice design, video dubbing and install via the official script.
Learn more
First spotted on github: source.
More AI models
MiniMind: train your own 64M LLM from scratch in about 2 hoursA complete, from-scratch LLM training pipeline at 64M parameters - pretraining, SFT, LoRA, DPO, PPO/GRPO, tool use and…models · JEV 0.82Edge0-145B: open 145B MoE that runs on a single consumer GPUEdge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that…models · JEV 0.74Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73tiny-voca: a fully open 4.5M-parameter TTS trained for under $10 of computeA fully open 4.5M-parameter English TTS — code, weights and dataset under Apache 2.0 — trained from scratch in 7.7…models · JEV 0.67Qwen4-Max: Alibaba's new flagship model goes liveAlibaba's 2.4T-parameter flagship is now generally available via API, with a 1M-token context, native vision, and…models · JEV 0.67Apple Depth Pro 2: sharp, temporally consistent metric depth for images and videoApple released Depth Pro 2, a family of four open-weight models (24M-872M) that estimate metric depth in meters from a…models · JEV 0.66
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.