agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/speech-to-text/SKILL.md

speech-to-text

Skill5 starsChanged 8 months agoMITView on GitHub

Transcribe audio files to text using local Whisper (no API key needed) or OpenAI Whisper API. Supports MP3, WAV, M4A, MP4, and more. Use when user says "transcribe this audio", "convert speech to text", "transcribe meeting", "what was said in audio.mp3", or any speech transcription request.

  • Reads credentials
  • Installs packages

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use speech-engine, dubbing and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • RobStrayerSkill

    speech-engine

    Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when building Speech Engine servers, WebSocket handlers, WebRTC browser clients, conversation token endpoints, interruption-aware streaming responses, or voice-enabled chat agents that connect developer-owned server logic to ElevenLabs speech-to-text and text-to-speech.

    Also in 3 projects that use this

  • perso-aiSkill

    dubbing

    Auto-dub (voice-translate) videos into other languages, with lip-sync (Perso AI Dubbing).

    Also in 4 projects that use this

  • RobStrayerSkill

    voice-isolator

    Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio isolation) API. Use when cleaning up noisy recordings, removing music or background ambience from dialogue, isolating speech from field recordings, preparing audio for transcription, extracting vocals, or any "denoise / clean up / isolate voice" task.

    Also in 3 projects that use this

  • wlzhSkill

    voice-changer

    音频变声处理工具 - 使用 RVC AI 模型进行真实的声音转换,支持视频直接输入

    Also in 3 projects that use this

  • bitwize-music-studioSkill

    sound-effects

    Makes a sound effect, a one-shot or a loop for an album through Suno's MCP server - rain for an intro, a riser, a vinyl crackle bed, a drum loop at a track's tempo. Shows the cost and waits for a go-ahead. Use when the user asks for "a sound of...", "an ambience", "a loop", "a sting" or "a sound effect" rather than a song.

    Also in 4 projects that use this

  • marswaveaiSkill

    music

    Generate, remix, extend, edit, and analyze AI music (Mureka). Triggers on: "音乐", "music", "生成音乐", "generate music", "翻唱", "cover", "混音", "remix", "续写", "extend", "纯音乐", "instrumental", "配乐", "soundtrack", "分轨", "stem", "识别歌词", "recognize lyrics", "作曲", "compose", "create a song", "做一首歌".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Default recommendation: base for speed, small for quality.

    line 49
  2. Distinctive:

    If local Whisper is too slow and you have an API key:

    line 110
  3. Very specific:

    Check if whisper is installed: which whisper || python3 -m whisper --help 2>/dev/null

    line 120
  4. Very specific:

    If not installed, show pip install openai-whisper and stop

    line 121
  5. Very specific:

    Check if ffmpeg is also installed: which ffmpeg

    line 122
  6. Very specific:

    Default to base model for files under 30 minutes, small for longer

    line 123
  7. Distinctive:

    Never display raw JSON output — summarize and show the transcript text

    line 128

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Speech to Text

Transcribe audio files locally using OpenAI Whisper — no API key required.

Prerequisites

Install local Whisper:

pip install openai-whisper
# Requires Python 3.8+

Also install ffmpeg (required by Whisper for audio processing):

brew install ffmpeg

First run downloads the model automatically to ~/.cache/whisper/.

Model sizes (speed vs accuracy tradeoff):

ModelSizeSpeedAccuracy
tiny39MBVery fastBasic
base74MBFastGood
small244MBModerateBetter
medium769MBSlowHigh
large1.5GBVery slowBest

Default recommendation: base for speed, small for quality.

Commands

Basic Transcription

whisper audio.mp3                          # Auto-detect language, base model
whisper audio.mp3 --model small            # Better accuracy
whisper audio.mp3 --language en            # Force English
whisper audio.mp3 --language zh            # Force Chinese
whisper audio.mp3 --language ja            # Force Japanese

Output Formats

whisper audio.mp3 --output_format txt      # Plain text
whisper audio.mp3 --output_format srt      # Subtitles with timestamps
whisper audio.mp3 --output_format vtt      # WebVTT subtitles
whisper audio.mp3 --output_format json     # Full JSON with timestamps
whisper audio.mp3 --output_format all      # All formats at once

Output Directory

whisper audio.mp3 --output_dir ~/transcripts/

Transcribe from Video

whisper meeting.mp4 --model small --output_format txt

Batch Transcription

whisper *.mp3 --model base --output_dir ./transcripts/

Usage Examples

"Transcribe meeting.m4a"

whisper meeting.m4a --model small --output_format txt --output_dir ./
cat meeting.txt

"Transcribe in Chinese"

whisper recording.mp3 --language zh --model small

"Generate subtitles for video.mp4"

whisper video.mp4 --model medium --output_format srt --output_dir ./

"Quick transcription (fast)"

whisper audio.mp3 --model tiny

OpenAI API Alternative

If local Whisper is too slow and you have an API key:

# Set key: export OPENAI_API_KEY=sk-...
curl https://api.openai.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1"

Rules

  • Check if whisper is installed: which whisper || python3 -m whisper --help 2>/dev/null
  • If not installed, show pip install openai-whisper and stop
  • Check if ffmpeg is also installed: which ffmpeg
  • Default to base model for files under 30 minutes, small for longer
  • Warn user if using medium or large — processing may take several minutes
  • Supported input formats: mp3, mp4, m4a, wav, ogg, flac, webm, mov
  • Output transcript file path in the response
  • For very long files (>1 hour), suggest splitting with ffmpeg first
  • Never display raw JSON output — summarize and show the transcript text

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.