Saltar al contenido
TakoAPI
Volver a skills

audio-processing

por iyeque

AI & LLMs
—Aún sin valoraciones
Tu valoración

Resumen

Audio ingestion, analysis, transformation, and generation (Transcribe, TTS, VAD, Features).

Descripción

Qué hace esta skill

Provides transcription, text-to-speech, voice activity detection, feature extraction, and audio transformation via a single command-line tool. Uses OpenAI Whisper for speech-to-text and Google TTS for synthesis. File paths are validated and system directory access is blocked.

Bundles five distinct audio operations into one tool so you don't need separate scripts for transcription, TTS, VAD, feature extraction, and transformation.

Cuándo usarla

  • Transcribe recorded meetings or interviews to text
  • Generate spoken audio from written content
  • Find speech segments in long recordings
  • Extract acoustic features for audio classification
  • Trim, normalize, or resample audio files in batch

Flujo de trabajo de ejemplo

ENTRADA

User asks: transcribe this interview recording and find where the speakers are talking

AGENTE
  1. 1

    Run transcribe action on the audio file using the small Whisper model

  2. 2

    Receive text transcript with timestamped segments

  3. 3

    Run vad_segments action on the same file to detect speech intervals

  4. 4

    Return transcript text alongside speech segment timestamps

SALIDA

Full text transcript plus a list of speech segments with start and end times

Instalación

clawhub install iyeque/audio-processing

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces