Documents, Media & Speech

Translate Studio also works with files, audio, and spoken output.

OCR

OCR (optical character recognition) extracts the text from an image or a scanned PDF. Upload the file and Translate Studio returns the text it contains, which you can then translate, summarise, or correct with the text tools.

Media

The Media tool pulls text out of a file or recording:

• Documents — extract the text content from an uploaded document.
• Audio — transcribe spoken audio into text.

Once you have the text, run any other Translate Studio tool on it.

Text to speech

Text to speech turns written text into natural-sounding audio. Pick from the available voices, paste your text, and generate the audio to download or play back. Speech generation is charged by the length of the text — see Billing → Credits.