Pular para o conteúdo
TakoAPI
Voltar às skills

elevenlabs-transcribe

por paulasjes

Speech & Transcription
2.1kDownloads informados pelo clawskills.sh
2Estrelas
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Transcribe audio to text using ElevenLabs.

Descrição

O que esta skill faz

Transcribes audio and video files to text using ElevenLabs Scribe. Supports batch processing of local files, realtime streaming from URLs or microphones, and speaker diarization across 90+ languages.

Handles both batch and realtime streaming in one tool, with speaker diarization and word-level timestamps that most transcription wrappers omit.

Quando usá-la

  • Transcribing recorded meetings with speaker labels
  • Capturing live voice input during an agent session
  • Converting podcast or radio streams to text in realtime
  • Extracting subtitles from video files with word timestamps
  • Batch transcribing interview recordings for analysis

Exemplo de fluxo de trabalho

ENTRADA

User asks: transcribe this meeting recording and identify who said what

AGENTE
  1. 1

    Receives meeting.mp3 as input

  2. 2

    Runs transcribe.sh meeting.mp3 --diarize --json

  3. 3

    ElevenLabs Scribe API processes the audio and returns speaker-labeled segments

  4. 4

    Parses JSON output to extract text grouped by speaker_id

  5. 5

    Returns formatted transcript with speaker attribution

SAÍDA

Full transcript with each speaker's lines labeled as speaker_0, speaker_1, etc., including word-level timestamps

Requisitos

  • ELEVENLABS_API_KEY environment variable
  • ffmpeg installed on the system

Instalação

clawhub install paulasjes/elevenlabs-transcribe

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links