Douyin
Parse posts, process batches, and archive assets locally
xiats · Content creation & multi-platform engagement
From inspiration to finished content
Create, publish and engage in one place
Collect assets and analyze videos, create with AI and talking avatars, publish across platforms, and manage engagement. Keep your assets, production, and account interactions in one toolkit, and pick up wherever you are in your workflow.
- Collect assets, transcribe dialogue, and keep prompts and shot references
- Create lip-synced avatars, AI videos, images, and scripts
- Manage publishing and engagement on desktop with tasks and logs
Assets & analysisCollect, transcribe, and find shot references
AI & talking avatarsScripts, images, and talking videos
Multi-platform publishingRuns in the desktop app
Engagement workspaceComment drafts and tasks for each account
Connect your content workflow in four steps
Start with source material, create and publish your content, then engage with your audience. Enter at whichever step you need.
01
Asset collection & video analysis
Organize platform assets, transcribe dialogue, and generate prompts and shot references.
Start with assets and references02
AI & talking avatar creation
Turn scripts, avatars, and voices into talking videos, or generate videos, illustrations, and product photos.
Keep your creative choices03
Multi-platform publishing
Manage publishing accounts, organize content, and review publishing tasks on desktop.
Runs in the desktop app04
Multi-platform comments
Prepare and edit AI comments per account, submit once, and review the results.
Windows desktop · VIP feature Asset collection · Video analysis
Keep assets and creative references together
Collect and organize assets by author and process them in batches on desktop. Use video analysis to transcribe dialogue and generate prompts and shot references before creating.
Xiaohongshu
Collect images, text, and videos; extract scripts and manage everything together
Bilibili, Kuaishou & more
Handle more popular content platforms in one workspace
Kuaishou logo source: kuaishou.com
Platform assets and local videosDialogue and content reviewPrompts and shot referencesContinue to AI & talking avatars
Web: Lightweight analysis
Choose original dialogue, an overall video prompt, or key shot references. Cloud models analyze the video directly, without local tools.
App: Capture inspiration anywhere
Use the same cloud analysis as the web app and choose the results you need. For detailed shot and motion analysis, switch to desktop.
Desktop: Detailed analysis
Process videos locally for dialogue, shots, expressions, motion, and editable generation prompts. Official mode needs no personal key; CYOK is also available.
Select only the stages you need. Prices are shown before starting. Web and mobile shot references do not provide exact cut timestamps.
Content ready? Keep publishing and engaging
Dedicated tools keep publishing tasks and account engagement easy to find.
Multi-platform publishing
Manage publishing accounts, organize content, and review task results in the desktop app. Supported platforms and content types depend on the current release.
- View accounts and publishing tasks together
- Runs locally and requires platform sign-in
- Web instructions and desktop app guidance
Multi-platform comments Windows · VIP
Manage accounts and generate or edit comments for each one. Click Run now once to submit. Tasks and logs show results by account.
- Comments available on Toutiao, Xiaohongshu, Douyin, Kuaishou, and Bilibili
- Likes, favorites, and follows vary by platform; see the app for current support
- One account per platform by default; each ¥10 purchase adds one permanent slot to every platform, with repeat purchases supported
- Task center shows the latest 30 tasks, newest first, with 10 per page and up to 3 pages
Version and availability: Comments require valid VIP membership and a Windows release with the comment workspace. See release notes for downloads. The website provides guidance; macOS and Android do not currently support the comment workspace. For bulk accounts, contact support on WhatsApp. Read about comments and account slots
See digital presenter results
Every video below was generated with xiats. All avatars are AI-generated, with no live filming.
Create a digital presenter video in three steps
Combine an avatar, a script, and a voice. Set up your avatar once; change only the script for each new video.
1
Choose an avatar
Upload a video of yourself facing the camera, or generate an AI character if you prefer to stay off camera.
Real footage: width and height 640–2048 pixels, fixed front-facing camera, about 30 seconds
2
Add a script
Extract speech from platform share links, upload a video for transcription, or ask AI to write a script.
Edit the script anytime and regenerate a video after even a one-line change
3
Choose a voice and generate
Pick a library voice or clone your own. The system adds voiceover and lip sync to produce the finished video.
Price shown before generation; full automatic refund on failure
- Only your own assetsUpload an authorized avatar or generate one with AI. The Platform does not collect other people's portraits for you.
- Temporary output storageGenerated files are temporary and retained for about 24 hours. Download them promptly.
- Credentials managed on the serverPlatform credentials are maintained in the backend and persisted in the database, without hardcoding or exposure.
- Two key modesManaged mode uses the official key. CYOK connects your own key, with requests and costs handled by your cloud account.
Why use xiats for talking avatars?
Create more than lip sync: manage your avatar, voice, script, and cost in one place.
No need to appear on camera
Four presets are available: an articulate female presenter, a professional male narrator, an energetic creator, and a 3D virtual character. All are AI-generated without real-person portrait licensing.
Clone your voice
Use a library voice or clone your own. Pair the same avatar with different voices and choose your presentation style.
No need to write from scratch
Extract speech from Xiaohongshu, Douyin, Bilibili, or Kuaishou links, or transcribe an uploaded video. AI can rewrite it into a more natural spoken script.
Know the cost before generation
Voiceover is billed by character count and lip sync by output duration. A confirmation dialog shows “Voiceover ¥X + Lip sync ¥Y = Approximately ¥Z” before generation, with no hidden charges.
Full automatic refunds on failure
Failed jobs are not charged. Reserved funds return to your wallet automatically, without contacting support.
One avatar, many videos
Record your avatar footage once. Change the script for each new video and generate in minutes, without setting up lighting and cameras again.
What people create
When the same person needs to deliver different messages repeatedly, talking avatars save time.
Product presentations
Create a presentation for each product using the same avatar, and prepare a batch for launch day.
Daily educational content
Turn topics into scripts and let an avatar present them, so daily publishing does not depend on filming.
Company communications & training
Keep product introductions, onboarding, and internal announcements consistent. Update the script to update the video.
Test different versions
Try variations in script and voice to see which performs best, paying only for the generated versions.
AI creation, more ways to express your ideas
Generate videos and images, process product photos, and refine topics and scripts. Video analysis has its own entry point. Web usage is billed per task, with prices shown before you begin.
Text to videoCreate a vertical short video from a description
Image to videoTurn a still image into a moving video
Text to imageGenerate an image from a text description
Image editingModify or extend an image with AI
Video extensionContinue a short video naturally
Video analysisExtract dialogue, generate prompts, and find shot references as needed
Titles & topicsGenerate titles and topic ideas with AI
Voice libraryManage and clone presentation voices
Video upscaling720p → 1440p AI super-resolution
Open Platform APICreate keys and call APIs yourself
Platforms supported for transcription
Paste a share link to turn video speech into text. More platforms are being added.
Xiaohongshu transcription
Douyin transcription
Bilibili transcription
Kuaishou transcriptionWatch a script become a video
Explore the updated workflow in about a minute: edit a script, choose an appearance and reference voice, set the frame size and review pricing. The final example is a real video previously created on the platform.
Apps & release notes
Exclusive to All-platform VIP: run long and batch digital presenter and AI creation tasks on your computer. CYOK connects your own model key, with requests and costs charged to your cloud account.
Use the video download Skill in an AI assistant
No desktop installation is needed. Sign in to the Open Platform with an active membership, create an API key, and select Use skill. Paste the installation prompt into an AI assistant that supports Skills.
The generic package contains no personal credentials. Calls require an active membership and API key. The installation prompt contains your credentials; share it only with an AI assistant you trust.
Refer to release notes for the available version. Multi-platform comments require valid VIP membership and a Windows release with the comment workspace. Likes, favorites, and follows vary by platform; consult the app for support.Capabilities differ by app. The engagement workspace is for Windows; macOS and Android are not currently supported. The Mac installer supports Apple M-series chips only.Current desktop frontend preview. Available features and versions depend on the release notes.Free to download. Using the client requires All-platform VIP membership.Desktop supports managed video understanding and AI creation without a personal key. CYOK requests and costs use your own Alibaba Cloud Model Studio account.Need your own key? Register with Alibaba CloudAndroid runs all AI generation in the cloud and charges your platform wallet by usage. No personal API key is needed.
Pricing
Membership and usage charges are separate. Membership unlocks unlimited text extraction and the desktop client; digital presenter creation is billed by usage.
How avatar generation is priced
- Voiceover: Billed by the script's character count.
- Lip sync: Billed by actual output duration, approximately equal to the voiceover length, with a minimum charge.
- Before generation, a dialog shows “Voiceover ¥X + Lip sync ¥Y = Approximately ¥Z” and your current balance. You are charged only after confirmation.
- Failed generation is fully refunded to your wallet automatically, without contacting support.
See the workspace price list for current rates. Sign in and open Digital presenter to view a quote.
Free
¥0.00/lifetime
Sign up and extract text from video links
Start free- Xiaohongshu / Douyin / Bilibili / Kuaishou
- Extract spoken text from a video link
- Automatically expand Douyin and Bilibili short links
- Batch extraction tasks and history
- Copy extracted text in one click
- No installation needed; works in mobile browsers
AI creation is billed by usage; desktop benefits follow current membership rules.
Recommended
All-platform VIP
¥39.90/month¥59.90
Unlimited text extraction on supported platforms
Membership benefitsUnlimited text extraction on supported platforms and applicable desktop benefits.
Includes desktop appAccess the complete workflow: parse, rewrite, synthesize and upscale.
- Unlimited text extraction on supported platforms
- Text extraction: upload a video to extract its script
- Web AI creation: text-to-video / image-to-video / text-to-image / image editing / video extension
- Digital human synthesis · Video upscaling
- Video understanding · Titles and topics · Voice library
- Desktop app · Complete workflow (parse / rewrite / synthesize / upscale)
- Priority extraction queue
- Dedicated technical support
Pay with WeChat Pay for automatic activation, with no manual confirmation needed.
All-platform VIP includes unlimited text extraction on supported platforms and applicable desktop benefits. Subscribe monthly for ¥39.90 or yearly for ¥399.00 via WeChat Pay.
AI creation is billed separately: text-to-video, image-to-video, digital human synthesis and upscaling are charged by usage from your wallet, with quotes shown before generation and automatic refunds on failure. Top up separately; membership does not include these charges.
Frequently asked questions
Start your next project with one asset
Analyze and create on the web, then switch to the desktop app for publishing when needed.
Register & start creating