Make a photo talk
Add a script, choose a photo avatar and select a voice. Save your authorized photos and voices to reuse in your next video.
Turn a script and photo into a talking avatar video, or edit a talking video you already have. Create in English and Chinese, with captions and a reusable visual style.
The same recording, with animated captions, highlights and paper-cut transitions.
This example uses a fictional presenter and synthetic narration.
Add a script, choose a photo avatar and select a voice. Save your authorized photos and voices to reuse in your next video.
Upload existing presenter footage up to 60 seconds. Keep the original voice and speaker, proofread the transcript and build the edit around it.
Choose a built-in layout or reuse a saved style. Custom styles stay private to your account. Creating new styles from reference videos is in preparation and is not available yet.
Preview the video, then adjust presenter size, caption placement or title timing. Review the new version before downloading.
Start with a script and authorized photo avatar, or upload a talking video. Choose English or Chinese speech. Script videos can run up to 10 minutes and uploads up to 60 seconds.
Pick a visual style and proofread your text or transcript. Review the task’s credit quote, then confirm generation.
Watch the preview and check names, captions and timing. Refine individual scenes, then download the finished video and captions.
Keep each video focused on one idea. Use these starting points to plan your script and choose the material you need.
Introduce one benefit with a photo avatar and voice, then use captions and on-screen labels to reinforce the details.
Write a short lesson in English or Chinese. Reuse your presenter and visual style to keep a series consistent.
Bring a talking video you have permission to use. Preserve the speaker and audio while adding readable captions and scene-level edits.
Buy credits when you need them. Each operation has a quote before you confirm it; the available payment options are shown on the pricing page.
Yes. Use a portrait you have permission to use, add your script and choose an available voice. You can save your own photo avatars and authorized voices for later projects. The video and any voice setup show their credit cost before confirmation.
Yes. Upload a talking video up to 60 seconds, review its transcript and choose a visual style. This path reuses the original speaker and audio, so you do not need to generate a new talking avatar.
The workflow supports English and Chinese speech, with script videos up to 10 minutes and uploads up to 60 seconds. Voice availability is shown in the studio. Always review pronunciation, names, subtitles and visual timing before publishing.
No reference video is required. Built-in layouts and your existing saved styles are available. Reference-video analysis for creating a new private style is in preparation and is not available yet. Saved custom styles are not listed for other users.
Credits pay for the operations you confirm, such as voice setup, speech generation, talking-avatar generation and video editing. Costs vary with the operation and duration. The studio shows a quote before each paid task; a pack is not a promise of a fixed number of finished videos.
Credit packs are one-time purchases: US$10 for 1,000 credits, US$30 for 3,000 and US$50 for 5,000. Purchased credits do not expire, and there is no automatic renewal. Available checkout methods are shown before you pay.
A technical failure restores the credits deducted for that operation. A completed result may still need your review or editing; starting a separate generation is a new paid operation. If the task status is unclear, check its status or contact support before starting again.