Vai al contenuto
TakoAPI
Torna alle skill

deepgram

di nerkn

Speech & Transcription
1.9kDownload riportati da clawskills.sh
1Stelle
0Visualizzazioni
0 likeAccedi per mettere like a questa skill
—Non ancora valutato
La tua valutazione

Sintesi

— command-line interface for Deepgram speech-to-text.

Descrizione

Cosa fa questa skill

Command-line interface for Deepgram speech-to-text. Transcribes local files, remote URLs, piped audio, or live microphone input. Outputs JSON, plain text, SRT, or VTT.

Pipe-friendly CLI design lets it slot into shell scripts and automation without any UI or SDK setup.

Quando usarla

  • Transcribe a recorded meeting to text
  • Generate subtitles for a video file
  • Dictate notes via microphone
  • Pipe audio from a script into a transcript
  • Separate speakers in an interview recording

Esempio di workflow

INPUT

User asks: transcribe interview.wav with speaker labels and save as text

AGENT
  1. 1

    Run deepgram login to authenticate with stored API key

  2. 2

    Run deepgram listen prerecorded interview.wav --model nova-2 --punctuate --diarize --format text

  3. 3

    Redirect output to transcript.txt

OUTPUT

Plain text transcript with speaker-separated lines saved to transcript.txt

Requisiti

  • Deepgram API key
  • Deepgram account (deepgram.com)

Installazione

clawhub install nerkn/deepgram

Esegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.

Link