SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

speakerAI272/speaker

Generates speech and presentation scripts with controllable duration and natural pacing. Key capabilities include: 1.…

No ratings yet Rate this skill
Stars460
Forks18
Watchers460
Open Issues1

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/AI272/speaker.git

OverviewOverview

Key Features

Generates speech and presentation scripts with controllable duration and natural pacing. Key capabilities include: 1. Pause-aware pacing model: budgets speech length by pause rhythm so read-aloud duration is deterministic and does not overrun; 2. Per-slide word budget: computes a word limit for each slide based on SKILL.md to prevent overloaded pages; 3. Glossary toggle: switches glossary on or off to keep terminology consistent; 4. Concise final delivery: trims the final script into a concise, ready-to-use version; 5. Document and slide parsing: uses python-pptx, python-docx and tesseract to extract text from PPT, Word and images as script source material.

Use Cases

controlling duration and per-page word count when preparing speech or briefing scripts, presentation materials that need consistent terminology, extracting content from existing PPT/Word/images for reworking, trimming scripts before delivery.

Target Roles

Content Creator / Social Media Operator, Product Manager (PM), Administrative / Secretarial Staff, Film/TV Director / Audio-Video Producer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1528
Data sourceGitHub
RepositoryAI272/speaker
CategoryVoice Interaction & IoT Skills / Smart Voice & Hardware Ecosystem
Primary languagePython
LicenseNot specified
Default branchmain
GitHub repository ID1258221473
Node IDR_kgDOSv7voQ
Rank#1369 (position within the source ranking)
Site-wide popularity rank#1551 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006002026-09-292026-10-112026-09-29 · 4592026-10-11 · 460
  • Now460
  • Previous point · 09-29 459
  • vs previous point +1
  • 2 data points 12 days
051015202026-09-292026-10-112026-09-29 · 182026-10-11 · 18
  • Now18
  • Previous point · 09-29 18
  • vs previous point ±0
  • 2 data points 12 days

TimelineTimeline

Repository created2026-06-03 11:33:335 months ago
Data last updated2026-10-26 12:13:1323 days ago
Last commit2026-06-23 12:25:554 months ago

CommitLatest commit

Version [v0.8.0] committed by AI272. Update Category: Feature Addition & Enhancement. Commit details: Release v0.8: pacing model, compact pipeline, concise output. This update introduces new capabilities and module extensions.

a7b5b9d v0.8.0 AI272 2026-06-23

Next stepsNext steps