How do I install the Speech To Text skill?

Run npx skillmds@latest add claude-world/speech-to-text in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Speech To Text safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Speech To Text?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Speech To Text free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Speech To Text?

claude-world (@claude-world) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Speech To Text by claude-world — Agent Skill

Name: Speech To Text
Author: claude-world

Speech To Text

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.

claude-world fcffd54 3.3 KB Updated Sep 17, 2026

File contents

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):

Model	Size	Speed	Accuracy
tiny	39MB	Very fast	Basic
base	74MB	Fast	Good
small	244MB	Moderate	Better
medium	769MB	Slow	High
large	1.5GB	Very slow	Best

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

---name: speech-to-textdescription: 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.---# Speech to TextTranscribe audio files locally using OpenAI Whisper — no API key required.## PrerequisitesInstall local Whisper:```bashpip install openai-whisper# Requires Python 3.8+```Also install ffmpeg (required by Whisper for audio processing):```bashbrew install ffmpeg```First run downloads the model automatically to `~/.cache/whisper/`.Model sizes (speed vs accuracy tradeoff):| Model | Size | Speed | Accuracy ||-------|------|-------|----------|| tiny | 39MB | Very fast | Basic || base | 74MB | Fast | Good || small | 244MB | Moderate | Better || medium | 769MB | Slow | High || large | 1.5GB | Very slow | Best |Default recommendation: `base` for speed, `small` for quality.## Commands### Basic Transcription```bashwhisper audio.mp3 # Auto-detect language, base modelwhisper audio.mp3 --model small # Better accuracywhisper audio.mp3 --language en # Force Englishwhisper audio.mp3 --language zh # Force Chinesewhisper audio.mp3 --language ja # Force Japanese```### Output Formats```bashwhisper audio.mp3 --output_format txt # Plain textwhisper audio.mp3 --output_format srt # Subtitles with timestampswhisper audio.mp3 --output_format vtt # WebVTT subtitleswhisper audio.mp3 --output_format json # Full JSON with timestampswhisper audio.mp3 --output_format all # All formats at once```### Output Directory```bashwhisper audio.mp3 --output_dir ~/transcripts/```### Transcribe from Video```bashwhisper meeting.mp4 --model small --output_format txt```### Batch Transcription```bashwhisper *.mp3 --model base --output_dir ./transcripts/```## Usage Examples**"Transcribe meeting.m4a"**```bashwhisper meeting.m4a --model small --output_format txt --output_dir ./cat meeting.txt```**"Transcribe in Chinese"**```bashwhisper recording.mp3 --language zh --model small```**"Generate subtitles for video.mp4"**```bashwhisper video.mp4 --model medium --output_format srt --output_dir ./```**"Quick transcription (fast)"**```bashwhisper audio.mp3 --model tiny```## OpenAI API AlternativeIf local Whisper is too slow and you have an API key:```bash# 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

Frequently asked questions