speech-to-text
Converts video files into timestamped text transcripts using an on-device Whisper model.
Install
mkdir -p .claude/skills/speech-to-text && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5805" && unzip -o skill.zip -d .claude/skills/speech-to-text && rm skill.zipInstalls to .claude/skills/speech-to-text
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Transcribe video to timestamped text using Whisper tiny model (pre-installed).Key capabilities
- →Transcribe video files to text
- →Generate timestamps for transcribed segments
- →Utilize pre-installed Whisper tiny model
How it works
The skill executes a Python script that processes video media through a pre-downloaded Whisper tiny model to generate time-indexed text.
Inputs & outputs
When to use speech-to-text
- →Generating transcripts from video files
- →Creating searchable logs for media content
- →Extracting text data from video tutorials
About this skill
Speech-to-Text
Transcribe video to text with timestamps.
Usage
python3 scripts/transcribe.py /root/tutorial_video.mp4 -o transcript.txt --model tiny
This produces output like:
[0.0s - 5.2s] Welcome to this tutorial.
[5.2s - 12.8s] Today we're going to learn...
The tiny model is pre-downloaded and takes ~2 minutes for a 23-min video.
When not to use it
- →Processing audio-only files without video tracks
Prerequisites
Limitations
- →Requires pre-installed Whisper tiny model
How it compares
It automates the extraction of synchronized timestamps directly from video files, whereas manual transcription requires separate timing and logging steps.
Compared to similar skills
speech-to-text side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| speech-to-text (this skill) | 7 | 2mo | Review | Beginner |
| feishu-drive | 3 | 6mo | No flags | Intermediate |
| calculator | 7 | 7mo | Review | Beginner |
| transactionsyncing | 1 | 5mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by benchflow-ai
View all by benchflow-ai →You might also like
feishu-drive
openclaw
Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.
calculator
Code-and-Sorts
Performs arbitrary-precision arithmetic calculations including addition, subtraction, multiplication, division, and exponents. Use when the user asks to calculate, compute, or evaluate math expressions, or when precise decimal arithmetic is needed to avoid floating-point errors.
transactionsyncing
AojdevStudio
Import Fidelity transaction history CSV into Google Sheets with smart categorization. USE WHEN user mentions "sync transactions", "import transactions", "transaction history", OR wants to import Fidelity History CSV. Routes debit card purchases to Expense Tracker with auto-categorization.
office-docs
Xxiii8322766509
Extract text and tables from .docx and .xlsx using local scripts (no external deps).
raffle-winner-picker
ComposioHQ
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
calc
Anhvu1107
ALWAYS use this when the request matches Calc: Spreadsheet creation, format conversion (ODS/XLSX/CSV), formulas, data automation with LibreOffice Calc.