Frequently asked questions about Translate audio and Translate video

Last updated on Feb. 17, 2025

Do you have more questions about Translate video and Translate audio? We've got you covered with answers to some of the common questions.

1. How will Content Credentials show up in the Translate video and Translate audio content?

Content Credentials will be attached to the content generated with Translate video and Translate audio so that people can see that generative AI was used in the creative process.

Content Credentials attached to the Translate video and Translate audio content will show that AI was used to generate speaker voices, translate between languages, and adjust new lip movements. 

2. Why can’t I edit the transcript before translating the audio while using the web app?

For our website, we decided to start with a simple approach for customers that supports the translation of audio. Please note that transcript editing is possible with our API.

3. How do I report the output that I find wrong, offensive, or harmful?

You can report negative or inaccurate results using the Report   tool.

4. When will you add more languages to Translate video and Translate audio? How can I get my language supported? 

We’re working on adding additional languages, but we don’t have any dates to share yet. If the language you use is currently unsupported, let us know using the Submit an idea button in the dropdown menu in the upper-right corner of the Adobe Firefly website or on Adobe Community Forum.

5. Why can’t I access Translate video and Translate audio in my location?

Adobe Firefly is only available in countries where Adobe services are available, subject to additional limitations that may apply.

6. What kind of recordings work best with Translate video and Translate audio?  

  • Your recording (video or audio) needs at least five seconds of spoken voice.

  • Recordings should have clear audio with audible speech and minimal reverb or background noise.

  • Currently, only single speakers are supported – multiple speakers taking frequent turns will give undesirable results. 

  • Recordings should have only one language spoken throughout. 

7. What are the technical specifications of video and audio files I can use?

You can translate and/or lip sync files that are a minimum of five seconds long, up to 10 minutes in length. The file must contain at least five seconds of continuous audio. 

For video files:

  • Input video support: Up to 4K resolution

  • Containers: .mp4 and .mov

For audio files:

  • Containers: .mp3, aac, and .wav

8. What file formats do Translate video and Translate audio create?

Output video files are .mp4 files, and audio files are .wav. 

9. How do I get my video or audio clip if I left the website during processing?

If you leave the Translate video and Translate audio module during processing, you can return up to 7 days later to view your processed media. The file is displayed in a thumbnail on the page when you navigate back to Translate video and Translate audio. 

Join our community to connect, learn, and engage

For inspiration, expert tips, and solutions to common issues, visit Discord or the Adobe Firefly Community forum. Connect with our team and fellow users to exchange ideas, share your creations, stay updated with the latest features and announcements, and provide feedback.