Перейти к содержимому
TakoAPI
Назад к навыкам

elevenlabs-transcribe

от paulasjes

Speech & Transcription
2.1kЧисло загрузок по данным clawskills.sh
2Звёзды
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Transcribe audio to text using ElevenLabs.

Описание

Что делает этот навык

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.

Когда его использовать

  • 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

Пример сценария

ВВОД

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

АГЕНТ
  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

ВЫВОД

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

Требования

  • ELEVENLABS_API_KEY environment variable
  • ffmpeg installed on the system

Установка

clawhub install paulasjes/elevenlabs-transcribe

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки