Frequently Asked Questions

DocuSpeaker is an AI-powered tool that turns your PDF documents into short video presentations. Upload a PDF, tell the AI what to focus on, and get a professional video with an AI avatar presenting the key insights.

DocuSpeaker accepts PDF files. This includes reports, research papers, presentations, articles, financial documents, and any other text-based PDF. The AI extracts the text content and uses it to generate your video script.

Videos are approximately 30–45 seconds long. The AI generates a concise script (80–95 words) that captures the most important insight from your document, keeping videos short and impactful.

DocuSpeaker supports over 50 languages including English, Hebrew, Spanish, French, German, Chinese, Japanese, Arabic, Portuguese, and many more. You can select your language before generating the script, and the AI will write and speak in that language.

Yes! After the AI generates a script, you can review and edit it freely before creating the video. You can rewrite it entirely or make small adjustments to get exactly what you want.

Yes. DocuSpeaker offers a selection of AI avatars and voices. You can pick the avatar that best fits your content and choose a voice that matches your selected language.

Yes. You can choose a solid background color or upload a custom background image for your video.

Script generation takes just a few seconds. Video rendering typically takes 1–5 minutes depending on the language and video settings. You can track progress in real time on screen.

The Pro plan includes 50 credits, Business includes 180 credits, and Enterprise includes 400 credits per month. Script generation costs 1 credit and translation costs 2 credits. Video generation is based on duration: 1 credit for every 5 seconds of video. For example, a 30-second video costs 6 credits and a 45-second video costs 9 credits. Unused credits do not carry over. Your credits reset automatically at the start of each billing cycle.

Yes. Once your video is ready, you can download it as an MP4 file and use it anywhere — in presentations, on social media, in emails, or on your website.

Yes. You can optionally upload a photo of yourself to use as a custom AI avatar instead of the built-in avatars. By uploading a photo you confirm you have the right to use it and consent to its use for video generation. Your photo is transmitted to our AI video provider (D-ID) solely to animate your avatar for the video. We do not use your photo for any other purpose, and you can request deletion at any time by emailing support@docuspeaker.com.

Your uploaded photo is stored temporarily in our secure cloud storage for the duration of video generation. It is sent to D-ID (our AI video provider) only to create your video. We do not perform facial recognition, biometric profiling, or any analysis of your image beyond what is needed to generate your video. We do not sell or share your photo with any third party other than D-ID for this purpose. Once generation is complete, the photo is no longer actively used. You can request its deletion by contacting support@docuspeaker.com.

Yes. Your uploaded PDFs are processed in memory and never stored on our servers. We use encrypted connections (HTTPS) and secure authentication. We do not share your documents or generated content with third parties beyond the AI services required to generate your video (Anthropic for scripts, D-ID for video). See our Privacy Policy for full details.

We accept all major credit cards, debit cards, and other payment methods supported by our payment provider. Payments are securely processed — we never see or store your card details.

Yes, you can cancel at any time from your account settings. Your access continues until the end of your current billing period. There are no cancellation fees.

Videos you’ve already downloaded are yours to keep. However, video links may expire after a period of time, so we recommend downloading your videos promptly after generation.

Contact us at support@docuspeaker.com and we’ll be happy to help.