How do I translate and dub audio or video?

Interpretation creates translated dubbing from uploaded audio or video. If you only need written transcription, choose Speech to Text.

1. Open Interpretation and upload the source file. Wait until the source is ready.
2. Select the target language or languages available on the page and check the project settings.
3. Review the quote for the selected targets and confirm the generation action. Watch the status for each target language.
4. When a target is complete, use the project’s available preview and export options. Reopen the project from History when needed.

If a target is missing, failed or still processing, identify that language and its visible state. Tell Support the project name, time and the step that failed. Available languages, export options and cost follow the current page.

Generating file dubbing requires a paid plan. File translation processes an existing audio track; it does not provide video lip-sync or dubbing by selecting a cloned voice from My Voice. For live interpretation or selecting a realtime translated voice, see Interpretation's realtime mode. The two modes have different operations, usage rules and result retention. Saving a file draft does not mean your plan can start generation. Only a source file with video can export an MP4 with video; choose an available format under a completed target language.