Communitygithub.com

Transcripción de Videos de YouTube

Transcribe videos de YouTube a texto usando OpenAI Whisper y yt-dlp. Útil cuando el usuario quiere obtener una transcripción de un video de YouTube, generar subtítulos, convertir audio de video a texto, crear subtítulos SRT/VTT o extraer contenido hablado de URLs de YouTube.

¿Qué es Transcripción de Videos de YouTube?

Esta habilidad permite transcribir automáticamente el contenido hablado de videos de YouTube a texto. Utiliza yt-dlp para descargar el audio de alta calidad y el modelo Whisper de OpenAI para transcribirlo con alta precisión. Soporta múltiples formatos de salida como TXT, SRT, VTT, TSV y JSON, y ofrece diferentes tamaños de modelo Whisper (tiny, base, small, medium, large) para adaptarse a las necesidades de velocidad y precisión. Es útil para desarrolladores, creadores de contenido y usuarios que necesitan acceder al texto de videos de YouTube, ya sea para subtitulado, análisis, documentación o accesibilidad. Funciona en cualquier sistema operativo con Python, ffmpeg y dependencias estándar.

Compatible con~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/TerminalSkills/skills/tree/HEAD/skills/youtube-transcription

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

¿Qué hace Transcripción de Videos de YouTube?

Transcribe videos de YouTube a texto usando OpenAI Whisper y yt-dlp.

Resumen

Esta habilidad descarga el audio de videos de YouTube usando yt-dlp y lo transcribe utilizando el modelo Whisper de OpenAI. Soporta múltiples formatos de salida (txt, srt, vtt, json) y varios tamaños de modelo para diferentes compensaciones entre precisión y velocidad.

Instrucciones

1. Instalar dependencias

# Instalar whisper y yt-dlp
pip install openai-whisper yt-dlp

# Verificar que ffmpeg esté instalado (requerido para procesamiento de audio)
ffmpeg -version

Si ffmpeg falta:

2. Descargar audio de YouTube

# Descargar la mejor calidad de audio como WAV
yt-dlp -x --audio-format wav -o "%(title)s.%(ext)s" "YOUTUBE_URL"

# Descargar como MP3 (archivo más pequeño)
yt-dlp -x --audio-format mp3 -o "%(title)s.%(ext)s" "YOUTUBE_URL"

# Descargar con ID de video como nombre de archivo (más seguro para caracteres especiales)
yt-dlp -x --audio-format wav -o "%(id)s.%(ext)s" "YOUTUBE_URL"

3. Elegir modelo Whisper

ModeloParámetrosVRAMVelocidad RelativaCaso de Uso
tiny39M~1 GB~32xBorradores rápidos, pruebas
base74M~1 GB~16xTranscripción rápida
small244M~2 GB~6xBuen equilibrio
medium769M~5 GB~2xAlta precisión
large1550M~10 GB1xMejor precisión

Los modelos solo inglés (tiny.en, base.en, small.en, medium.en) son más rápidos para contenido en inglés.

4. Ejecutar transcripción

Enfoque CLI:

# Transcripción básica (detección automática de idioma)
whisper audio.wav --model medium

# Especificar idioma para mayor precisión
whisper audio.wav --model medium --language en

# Formato de salida específico
whisper audio.wav --model medium --output_format srt

# Todos los formatos a la vez
whisper audio.wav --model medium --output_format all

# Especificar directorio de salida
whisper audio.wav --model medium --output_dir ./transcripts

Enfoque Python:

import whisper

# Cargar modelo (descarga en la primera ejecución)
model = whisper.load_model("medium")

# Transcribir
result = model.transcribe("audio.wav", language="en")

# Obtener texto plano
print(result["text"])

# Obtener segmentos con marcas de tiempo
for segment in result["segments"]:
    print(f"[{segment['start']:.2f} - {segment['end']:.2f}] {segment['text']}")

5. Tubería de un solo comando

Combinar descarga y transcripción:

# Descargar y transcribir en un solo comando
yt-dlp -x --audio-format wav -o "audio.wav" "YOUTUBE_URL" && whisper audio.wav --model medium --output_format all

6. Alternativa: herramienta yt-whisper

Para un flujo de trabajo más simple, usa el paquete dedicado yt-whisper:

# Instalar
pip install git+https://github.com/m1guelpf/yt-whisper.git

# Transcribir directamente desde URL
yt_whisper "https://www.youtube.com/watch?v=VIDEO_ID"

# Con opciones
yt_whisper "YOUTUBE_URL" --model medium --language en --output_format srt

Formatos de Salida

FormatoExtensiónDescripción
txt.txtTranscripción en texto plano
srt.srtFormato de subtítulos SubRip (con marcas de tiempo)
vtt.vttFormato de subtítulos WebVTT
tsv.tsvValores separados por tabulaciones
json.jsonDatos completos con marcas de tiempo a nivel de palabra

Ejemplos

Buenas Prácticas

  • Usa la bandera --language cuando sepas el idioma hablado para obtener una precisión significativamente mejor.
  • Para videos largos (>1 hora), usa el modelo small o medium para equilibrar velocidad y precisión.
  • Los modelos solo inglés (sufijo .en) son más rápidos y precisos para contenido en inglés.
  • Una GPU con CUDA acelera drásticamente la transcripción; la CPU funciona pero es 5-10 veces más lenta.
  • Si la transcripción falla, asegúrate de que ffmpeg esté instalado correctamente y en el PATH.
  • Para videos con música de fondo, los modelos más grandes (medium/large) manejan mejor la situación.
  • Limpia los archivos de audio después de la transcripción para ahorrar espacio en disco.
  • Usa --output_format all para obtener todos los formatos a la vez, luego elige el que necesites.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

TerminalSkills/skills

>- Run GitHub Actions locally with act. Use when a user asks to test GitHub Actions workflows locally, debug CI pipelines without pushing, or run workflows offline.

TerminalSkills/skills

>- You are an expert in AG2 (formerly AutoGen), the open-source multi-agent conversation framework. You help developers build systems where multiple AI agents collaborate through structured conversations — with tool use, human-in-the-loop, code execution, group chat orchestration, and nested conversations — for complex tasks like software development, research, and data analysis.

TerminalSkills/skills

>- Generate short-form videos with AI — script writing, text-to-speech narration, stock footage selection, subtitle generation, and video assembly. Use when: creating TikTok/YouTube Shorts/Reels content, automating video production, building content pipelines.

TerminalSkills/skills

>- Animate 3D objects and characters in Blender with Python. Use when the user wants to keyframe properties, create armatures and rigs, set up IK/FK chains, animate shape keys for facial animation, edit F-Curves, use the NLA editor to blend actions, add drivers for expression-based animation, or script any animation workflow in Blender.

TerminalSkills/skills

>- Automate motion capture and tracking workflows in Blender with Python. Use when the user wants to import BVH or FBX mocap data, retarget motion to armatures, track camera or object motion from video, solve camera motion, clean up motion capture data, or script any tracking pipeline in Blender.

TerminalSkills/skills

>- You are an expert in Bolt.new by StackBlitz, the AI-powered full-stack development environment that runs entirely in the browser. You help developers go from idea to deployed app in minutes using natural language prompts — Bolt generates complete applications with frontend, backend, database, and deployment, all running in a WebContainer without local setup.

TerminalSkills/skills

>- Assists with using Bun as an all-in-one JavaScript/TypeScript runtime, package manager, bundler, and test runner. Use when building HTTP servers, managing packages, running tests, or migrating from Node.js. Trigger words: bun, bun serve, bun install, bun test, bun build, javascript runtime, bun runtime.

TerminalSkills/skills

>- Self-host customer support with Chatwoot. Use when a user asks to set up open-source customer support, add live chat without SaaS costs, build a multi-channel inbox, or deploy a free Intercom alternative.

TerminalSkills/skills

>- You are an expert in Chi, the lightweight, idiomatic Go HTTP router built on `net/http`. You help developers build composable HTTP services using Chi's middleware stack, route groups, URL parameters, sub-routers, and context-based request scoping — providing Express-like ergonomics while staying 100% compatible with Go's standard library.

TerminalSkills/skills

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

TerminalSkills/skills

>- Add live chat and customer support with Crisp. Use when a user asks to add a chat widget, implement live customer support, set up a help desk, create a knowledge base, or add a chatbot to a website.

TerminalSkills/skills

>- Assists with building custom interactive data visualizations using D3.js. Use when creating charts, graphs, maps, force layouts, or hierarchical diagrams that require fine-grained control beyond what charting libraries provide. Trigger words: d3, data visualization, chart, svg, scales, force graph, treemap, choropleth.

TerminalSkills/skills

dbt (data build tool) transforms data in your warehouse using SQL SELECT statements. Learn project setup, models, tests, documentation, incremental materializations, and integration with data warehouses like PostgreSQL, BigQuery, and Snowflake.

TerminalSkills/skills

>- You are an expert in dlt, the open-source Python library for building data pipelines. You help developers load data from any API, file, or database into warehouses and lakes using simple Python decorators — with automatic schema inference, incremental loading, and built-in data contracts. dlt is the "requests library for data pipelines.

TerminalSkills/skills

Data Version Control for ML projects. Track large datasets and models alongside Git, build reproducible ML pipelines, and run experiments with metric comparison. Works with any storage backend including S3, GCS, Azure, and local filesystems.

TerminalSkills/skills

>- You are an expert in E2B, the cloud platform for running AI-generated code in secure sandboxes. You help developers give AI agents the ability to execute code, install packages, read/write files, and run long processes in isolated cloud environments — each sandbox is a lightweight VM that boots in ~150ms with full Linux, filesystem, and networking.

TerminalSkills/skills

>- Transcode, convert, edit, and process audio and video with FFmpeg. Use when a user asks to convert video formats (webm to mp4, mkv to mp4), extract audio from video, compress video files, trim or cut clips, concatenate videos, add subtitles, create thumbnails, apply filters, change resolution or bitrate, re-encode media, create GIFs from video, add watermarks, normalize audio, stream media, or build automated media processing pipelines.

TerminalSkills/skills

>- Create advanced animations with GSAP. Use when building complex timelines, scroll-driven animations, SVG morphing, text animations, or high-performance web animations beyond CSS capabilities.

TerminalSkills/skills

>- Generate deterministic MP4 videos from HTML, CSS, media, and seekable animations using HeyGen's HyperFrames framework. Use when someone asks to "render HTML to video", "make a video with HyperFrames", "create a programmatic video", "turn an animation into MP4", "build a launch/product video from HTML", "render GSAP/Lottie/Three.js to video", or set up an agent-driven video pipeline. Covers init/preview/render/add/lint/inspect commands, data-* timing attributes, animation adapters, and the component catalog.

TerminalSkills/skills

When the user wants to perform load testing, stress testing, or performance testing of APIs and websites using k6. Also use when the user mentions "k6," "load test," "performance test," "stress test," "spike test," "soak test," "thresholds," "virtual users," or "VUs." For browser-based testing, see selenium.

Skills relacionados