SkillAgentSearch skills...

whisper-transcription

Transcribe audio/video to text with word-level timestamps using OpenAI Whisper

Install / Use

npx skills add benchflow-ai/skillsbench --skill whisper-transcription

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

82/100

Supported Platforms

Universal

Tags

Our assessment of whisper-transcription

whisper-transcription scores 82/100 on our quality scale, 3255th of 4,700 Development & Engineering skills we index.

Its SKILL.md is 4.4 KB long, well organised into 11 sections with 6 code examples: a solid amount of guidance for an agent.

With 1,813 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
20/20
Description
12/15
Adoption
14/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-11-07 found the source still online.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 98/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

whisper-transcription compared with similar skills

All 4 of these similar skills score higher than whisper-transcription; compare them before choosing.

SkillScoreStarsUpdatedFormat
whisper-transcription (this skill)by benchflow-ai821.8k4mo agoSKILL.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
ai-job-searchby ai-job-search-dev10072.1ktodayCLAUDE.md
claude-howtoby luongnv8910047.3k2d agoCLAUDE.md
lobehubby lobehub10085.6ktodayMCP Server

Frequently asked questions

How do I install whisper-transcription?
Run npx skills add benchflow-ai/skillsbench --skill whisper-transcription. The install tabs above show the steps for each supported agent.
Which AI agents does whisper-transcription work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is whisper-transcription safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 98/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is whisper-transcription still maintained?
The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

name: whisper-transcription description: "Transcribe audio/video to text with word-level timestamps using OpenAI Whisper. Use when you need speech-to-text with accurate timing information for each word."

Whisper Transcription

OpenAI Whisper provides accurate speech-to-text with word-level timestamps.

Installation

pip install openai-whisper

Model Selection

Use the tiny model for fast transcription - it's sufficient for most tasks and runs much faster:

| Model | Size | Speed | Accuracy | |-------|------|-------|----------| | tiny | 39 MB | Fastest | Good for clear speech | | base | 74 MB | Fast | Better accuracy | | small | 244 MB | Medium | High accuracy |

Recommendation: Start with tiny - it handles clear interview/podcast audio well.

Basic Usage with Word Timestamps

import whisper
import json

def transcribe_with_timestamps(audio_path, output_path):
    """
    Transcribe audio and get word-level timestamps.

    Args:
        audio_path: Path to audio/video file
        output_path: Path to save JSON output
    """
    # Use tiny model for speed
    model = whisper.load_model("tiny")

    # Transcribe with word timestamps
    result = model.transcribe(
        audio_path,
        word_timestamps=True,
        language="en"  # Specify language for better accuracy
    )

    # Extract words with timestamps
    words = []
    for segment in result["segments"]:
        if "words" in segment:
            for word_info in segment["words"]:
                words.append({
                    "word": word_info["word"].strip(),
                    "start": word_info["start"],
                    "end": word_info["end"]
                })

    with open(output_path, "w") as f:
        json.dump(words, f, indent=2)

    return words

Detecting Specific Words

def find_words(transcription, target_words):
    """
    Find specific words in transcription with their timestamps.

    Args:
        transcription: List of word dicts with 'word', 'start', 'end'
        target_words: Set of words to find (lowercase)

    Returns:
        List of matches with word and timestamp
    """
    matches = []
    target_lower = {w.lower() for w in target_words}

    for item in transcription:
        word = item["word"].lower().strip()
        # Remove punctuation for matching
        clean_word = ''.join(c for c in word if c.isalnum())

        if clean_word in target_lower:
            matches.append({
                "word": clean_word,
                "timestamp": item["start"]
            })

    return matches

Complete Example: Find Filler Words

import whisper
import json

# Filler words to detect
FILLER_WORDS = {
    "um", "uh", "hum", "hmm", "mhm",
    "like", "so", "well", "yeah", "okay",
    "basically", "actually", "literally"
}

def detect_fillers(audio_path, output_path):
    # Load tiny model (fast!)
    model = whisper.load_model("tiny")

    # Transcribe
    result = model.transcribe(audio_path, word_timestamps=True, language="en")

    # Find fillers
    fillers = []
    for segment in result["segments"]:
        for word_info in segment.get("words", []):
            word = word_info["word"].lower().strip()
            clean = ''.join(c for c in word if c.isalnum())

            if clean in FILLER_WORDS:
                fillers.append({
                    "word": clean,
                    "timestamp": round(word_info["start"], 2)
                })

    with open(output_path, "w") as f:
        json.dump(fillers, f, indent=2)

    return fillers

# Usage
detect_fillers("/root/input.mp4", "/root/annotations.json")

Audio Extraction (if needed)

Whisper can process video files directly, but for cleaner results:

# Extract audio as 16kHz mono WAV
ffmpeg -i input.mp4 -vn -acodec pcm_s16le -ar 16000 -ac 1 audio.wav

Multi-Word Phrases

For detecting phrases like "you know" or "I mean":

def find_phrases(transcription, phrases):
    """Find multi-word phrases in transcription."""
    matches = []
    words = [w["word"].lower().strip() for w in transcription]

    for phrase in phrases:
        phrase_words = phrase.lower().split()
        phrase_len = len(phrase_words)

        for i in range(len(words) - phrase_len + 1):
            if words[i:i+phrase_len] == phrase_words:
                matches.append({
                    "word": phrase,
                    "timestamp": transcription[i]["start"]
                })

    return matches

Related Skills

View on GitHub
GitHub Stars1.8k
CategoryDevelopment
Updated3mo ago
Forks368

Languages

PDDL

Trust signals

98/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 info