FAQs

Can I Use Deep Word For Free?

Yes, you can! We offer a free plan to all our users when they sign up. This plan allows you to create up to 2:00 minutes worth of video (with certain feature restrictions), with each video being up to one minute long. However, we also offer paid plans for those who need to produce longer and more frequent videos. For more information, check out our pricing page.

How do I use DeepWord?

Deep Word is super simple. Here is a quick video tutorial. After logging in or creating your account, you will be taken to your Deep Word dashboard. From here click on ‘Create New’, to create a Deep Word video. Next, upload or select your video video actor (short video of the person you want talking). You can either select one of our video actors, upload your own video, or import one using a Youtube URL. Then, select, type, or upload the audio you want your video actor to say. You can either select one of our audio samples, type the text you want your video actor to speak (select a voice and language), or upload an audio file from your local computer or Youtube URL. After clicking on ‘Generate Video’ you will be taken back to your Deep Word dashboard where you can view the processing status of the video you just created. Videos usually finish processing within 5-15 minutes depending on the length of your final video. Once this is complete, your video’s status will change from ‘Processing’ to ‘Complete’. You are now free to view, download, or share your video by clicking on it in your Deep Word dashboard. You can visit our How It Works page for a comprehensive set of upload guidelines for your video actors and audio.

How do Deep Word video minutes work?

Your Deep Word video minute balance is a measure of the amount of video you can generate with your account, either on our website or through our API. The length of your generated video is based upon the length of the audio you want your video actors to speak. For example, if you type or upload an audio file that is 59 seconds long, your generated video will be 59 seconds long, and your account balance will be subtracted by 1 video minute (charged in 10-second increments). For more information, please view our pricing page.

Will my video minutes carry over?

If you directly purchase Deep Word video minutes (pay as you go), your minutes will never expire on Deep Word meaning that they will carry over month to month in perpetuity. If you have purchased a premium monthly subscription, your video minutes will automatically be reset every month to 14, meaning that they will not carry over. For more information, please view our pricing page.

How do I use the Deep Word API?

Visit our API documentation page for full Deep Word API set up and instructions (text and video tutorials). The documentation also includes tutorials on how to generate templated personalized videos for lists of CSV contacts, how to integrate with your own native applications, and much more. To get started, you’ll either need to purchase a premium subscription or video minutes. Then, simply log into your Deep Word account (if you aren’t already) and click on the API tab on the left. From here you’ll be able to generate your API and secret keys to access Deep Word API.

What audio and video formats are supported?

Deep Word should work with any and all audio and video file formats. However, our officially supported audio formats are WAV, MP3, M4A, WMA, and FLAC. Our officially supported video formats are MP4, MOV, WEBM, FLV, AVI, and MKV. If for some reason Deep Word is returning an error when you try to upload or process one of these formats, please contact us here or via the support tab in your account.

What video and audio inputs work best with Deep Word?

For video actors, we recommend:
- Not too close. Not too far. 5-10 feet away from the camera is optimal, approximately waist up.
- Looking directly at the camera.
- Stationary (seated or standing) and not moving excessively.
- Against a solid colored background, that contrasts the clothing and skin tone of the actor.
- Actor’s lips should not be moving, but they can be making facial expressions and hand gestures as long their head is not moving very much.
- No obstructions to the nose, lips, or jaw. Even a single rogue frame can produce poor results.
For audio inputs, we recommend:
- Audio with little to no background noise.
- Stable audio levels. No spikes or clipping of gain.
- Can be in ANY language.

What video and audio inputs work best with Deep Word?

Deep Word Text-to-Speech offers 129+ languages and over 330 voices Here is a full list of these. However, via audio upload, videos can be generated in any language. We support all major languages and dialects used worldwide.

How does DeepWord prevent harmful content from being made on their platform?

DeepWord enables companies and creators to produce synthetic media, allowing them to scale and streamline their productions. We are aware of the bad things that can be created with this same tool. All content produced through DeepWord is monitored for malicious intent and the formulation of disinformation. Read more on our Ethics page.