Xiaohongshu wealth FAQ
One talking clip per written product answer
Xiaohongshu Wealth FAQ Talking reads the questions buyers ask on public Xiaohongshu wealth FAQ notes and records the product answers you already wrote as talking clips from your presenter portrait or product graphic. You get 2 to 8 separate MP4 clips of 2 to 15 seconds each, one per question, in a library voice or a voice clone of your own voice. Xiaohongshu Wealth FAQ Talking works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Xiaohongshu Wealth FAQ Talking and tell me when I need to sign in: https://beatra.ai/skills/xiaohongshu-wealth-faq-talking/install.md
For agents:Install guideMarkdown version
Send it to WorkBuddy, Codex, Claude Code, or another agent to install. Sign in once the first time you use it.GitHub ↗Docs ↗
FAQ reads the advisor can post separately
Speak only the written answer
Record only the product line the advisor already wrote.
One question, one clip
Each chosen note question becomes its own talking clip.
Hand off separate files
Deliver each wealth FAQ talking clip as its own file.
How it is made
Start from the public notes or pasted questions
Use the notes you can open or the questions already copied, then make one clip for each written product answer.
Keep the note sourced · Reuse the already-written product answer · Make one clip for each question
Turn those answers into short clips
Make one talking FAQ clip per note question so the pack stays separate files.
Keep spoken lines factual · One still, one clip · Keep the clips aligned with the written answer
Opening question, product beat, and close
Opening question
Open on the already-written answer to the first note question.
Product beat
Keep the printed product fact the advisor already named on the next clip.
Close
End on the close line they already wrote.
Inputs and outputs
Input · Text — Note questions to read or already copied, plus the product answers you wrote
Input · Image — A presenter portrait or product graphic for the first frame
- Formats
- JPG, PNG
Input · Audio — A sample of your own voice to clone (optional)
- Formats
- MP3, WAV
- Specifications
- 10–300 s; up to 20 MB each
Output · Video — One talking FAQ clip per question, each a separate file
- Formats
- MP4
- Specifications
- 2–8 videos per request; 2–15 s
Output · Audio — Spoken answer for each clip
- Formats
- MP3
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Text — Note questions to read or already copied, plus the product answers you wrote | — | — |
| Input | Image — A presenter portrait or product graphic for the first frame | JPG, PNG | — |
| Input | Audio — A sample of your own voice to clone (optional) | MP3, WAV | 10–300 s; up to 20 MB each |
| Output | Video — One talking FAQ clip per question, each a separate file | MP4 | 2–8 videos per request; 2–15 s |
| Output | Audio — Spoken answer for each clip | MP3 | — |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Questions
What do I need to start?
Public Xiaohongshu wealth FAQ notes or pasted questions, the product answers you already wrote, and a presenter photo or product graphic.
Is each question its own clip?
Yes. Each question becomes one talking FAQ clip, saved as a separate file.
Can I use my own voice?
Yes. A voice clone of your own voice can speak the answers in these clips.
Related Skills
