Dubbing in their own voice
Whisper transcribes, Opus-MT translates and OmniVoice clones the voice of each person in the video. The voice stays in sync with the picture.
Translay
Translate and dub videos from English into Spanish in each person's own voice. Everything runs on your machine, on your GPU.
YouTube and files
Paste a link, a playlist or a CSV with thousands of links; they are downloaded and processed automatically in a queue.
Libraries
Collections, channels, categories and search across all transcripts. Each library in its own folder.
Desktop app
A Windows installer: the app sets up Python, the server and the voice engine by itself, and opens Translay in its own window.
API and webhooks
Everything the app does is also available over HTTP, with per-library keys and signed notifications.
What it looks like
Section titled “What it looks like”
The screenshots come from a test instance with public-domain videos from NASA and NOAA.
Where to go next
Section titled “Where to go next”- Installation on Windows with the installer, from source or with Docker.
- Your first video, from pasting the link to hearing it in Spanish.
- How it works under the hood, if you plan to modify it.
- Changes in each version and the published releases.
- The code, bug reports and proposals, on GitHub.