Skip to main content
Gcore ASR transcribes speech from video into captions and translates those captions into more than 100 languages — handling recordings with multiple speakers or code-switching between languages in a single track. It works with MP4 videos hosted on Gcore Video Hosting or accessible via a public URL. To request support for a language not yet listed, contact Gcore support. The video below shows captions generated by Gcore ASR:

​
Data processing

Gcore processes all audio using Whisper on Gcore infrastructure — no files are transferred to external services. After a task completes, all source files are deleted from the AI system’s local storage.

​
Generate and translate AI captions

AI tasks run through the Gcore Customer Portal or the Streaming API. The Customer Portal guide covers creating a task, tracking its status, and downloading the generated captions.