timoncool /
speech-studio
Free offline AI voice studio for Windows — text-to-speech with cloned and built-in voices, and speech recognition with speakers. Russian done right. 100% local, one native .exe, zero Python.
Updated 26 min ago
Maintain this repo? Add this badge to your README.
Why now
Version v0.3.5 came out on October 28.
+82 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
It needs Windows, macOS on Apple silicon, or Linux with an NVIDIA GPU, Vulkan or Metal, and uses one native app with no Python installed. Speech recognition covers recordings, videos and links, and live mode uses an MCP agent.
Summary written by AI from the repository’s description and README.
timoncool / speech-studio
View on GitHub(opens in new tab)