Geography place talking clips
Read the place table with one short clip per photo
Geography Place Talking Clips turns your geography place table and presenter, map, or place photos into one short talking clip per photo. Each clip runs 2 to 15 seconds and speaks the place facts printed on your table, with 2 to 8 clips in a pack. Geography Place Talking Clips works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Geography Place Talking Clips and tell me when I need to sign in: https://beatra.ai/skills/geo-place-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 ↗
Name, feature, and classroom clips the teacher can post separately
Keep the table honest
Speak only the place facts already on the table the teacher supplied.
One photo, one clip
Each still becomes its own 2–15s talking clip.
Hand off separate files
Deliver name, feature facts, and classroom use as their own clips.
How it is made
Start from facts already on the table
Use authorized stills and the place table the teacher brought, then line the clips up as separate reads.
Look at each photo · Reuse the printed place lines · Keep each clip on one still
Give each still its own spoken clip
Animate one still at a time so the teacher can post name, facts, and classroom use separately.
Write a speakable line · One still, one clip · Review spoken facts after delivery
Place name, printed facts, and classroom use reads
Place name
A presenter still names the place already printed on the table.
Feature facts
A map or place photo speaks the landform or feature facts already on that row.
Classroom use
A last still speaks the classroom note the place table already shows.
Inputs and outputs
Input · Image — Presenter portrait, map, or place photo, one per clip
- Formats
- JPG, PNG
- Specifications
- up to 8 images per request
Input · Text — Your geography place table
Input · Audio — Voice sample for a cloned voice (optional)
- Specifications
- 10–300 s; up to 20 MB each
Output · Video — One talking clip per photo
- Formats
- MP4
- Specifications
- 2–8 videos per request; 2–15 s
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Image — Presenter portrait, map, or place photo, one per clip | JPG, PNG | up to 8 images per request |
| Input | Text — Your geography place table | — | — |
| Input | Audio — Voice sample for a cloned voice (optional) | — | 10–300 s; up to 20 MB each |
| Output | Video — One talking clip per photo | MP4 | 2–8 videos per request; 2–15 s |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Questions
What do I need to start?
At least one presenter, map, or place photo and the geography place table you already have.
Is each photo its own clip?
Yes. Each photo becomes its own short talking clip, and the clips stay separate.
Which voice reads the clips?
A voice you pick from the catalog, or one cloned from a 10-second to 5-minute sample.
Related Skills
