k2-fsa/OmniVoice

Source
GitHub
First trending
Category
Media
GitHub stars
13,381
Main language
Python

This page introduces an external open-source repository. It is not an HDATF product.

k2-fsa/OmniVoice

What it does

A zero-shot text-to-speech model covering more than 600 languages. It supports voice cloning, voice design through speaker attributes such as gender, age and accent, and pronunciation correction, with a Python API and command-line tools.

How it helps ATF

Only loosely related to our products. It could be a reference for multilingual text-to-speech, such as reading documents or messages aloud in a shared workspace like ATF Works.

License

Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.

More in this category

  • ArcReel/ArcReel
    A self-hosted workspace that turns novels, scripts or product materials into characters, scenes, props, storyboards and short videos. An agent can run each stage, users can review or regenerate it, and generation costs are tracked.
  • webadderallorg/Recordly
    A desktop app for recording and editing screen captures for demos and walkthroughs. It adds automatic zooms, smooth cursor movement, webcam overlay bubbles, styled frames and timeline editing.
  • tonhowtf/omniget
    OmniGet is a desktop app built on yt-dlp that downloads online courses, videos, music and books from many sites. It includes a course player, a PDF and EPUB reader, a music library and an MCP server.
  • crmne/spotifast
    Spotifast is a native Spotify client written in Rust with egui that plays music through librespot and appears as a Spotify Connect device. It runs on Linux, macOS and Windows, and playback needs Spotify Premium.
  • latent-spaces/brag
    brag is a Claude Code skill that turns a finished project into a short, shareable launch video with music, motion and share copy. The same skill is also exposed to other agents such as Codex CLI and opencode.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.

View on GitHub (opens in a new tab)