Voice cloning went fully local. voicestudio, the open-source elevenlabs alternative, runs cloning,…
voice cloning went fully local. voicestudio, the open-source elevenlabs alternative, runs cloning, dubbing and transcription on your own hardware across 646 languages.
the hosted ais have a local rival now.
Context
The VoiceStudio repository on GitHub (debpalash/VoiceStudio, formerly OmniVoice-Studio per its README, created April 9, 2026) is licensed under AGPL-3.0, with a commercial license offered for proprietary use. Its README says it does real-time dictation, zero-shot voice cloning from a 3 second clip and video dubbing, with no accounts, API keys or cloud, in 646 languages. It lists 14 text-to-speech engines and 11 speech recognition engines, a model store that detects CUDA, Apple Silicon, ROCm or CPU, and 10 GB of free disk for models and cache.
The 646 languages figure and the ElevenLabs comparison table (price, 32 languages, cloud-only dubbing) are the README's own marketing and were not checked against ElevenLabs pages or tested language by language. Fully local covers inference after models are downloaded, and the initial download needs network access. Each engine's own license was not inspected and may differ from the repo's AGPL. Star counts differ across sources and windows, 9,708 on the repo page as fetched on October 4, 2026, and are not used here.
Related work
- VoiceStudio and the star-growth claim ↗The earlier note on the same repo. It cites +15,895 stars in a month, which was not verified. This note is about language count and local scope.
Watch next
- The repo's per-engine license table, tagged releases, and a dated note on the rename.
Sources
- debpalash/VoiceStudio on GitHubgithub.com
- VoiceStudio sitevoicestudio.sh
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 18:35 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →