Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

whisnap

bởi neolio42

Coding Agents & IDEs
381Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

macOS CLI for transcribing audio and video files using local Whisper models or Whisnap Cloud.

Mô tả

Kỹ năng này làm gì

macOS CLI tool for transcribing audio and video files using local Whisper models or Whisnap Cloud. Requires the Whisnap desktop app with at least one model downloaded. Outputs plain text or structured JSON with timestamps.

Local model transcription keeps audio private on-device, while the cloud option is available when speed matters, all from a single CLI command.

Khi nào nên dùng

  • Transcribe recorded meetings to text
  • Extract captions from lecture recordings
  • Script batch transcription of interview files
  • Get timestamped segments from podcast audio
  • Transcribe screen recordings locally without uploading

Quy trình ví dụ

ĐẦU VÀO

User asks: transcribe a meeting recording and get timestamped JSON output

AGENT
  1. 1

    Run whisnap meeting.mp4 --json to start transcription using the default local model

  2. 2

    Whisnap reads the file and processes it through the downloaded Whisper model

  3. 3

    Structured JSON is written to stdout with full text, per-segment timestamps, model name, and processing time

  4. 4

    Pipe stdout to a file or downstream tool for further processing

ĐẦU RA

JSON object with `text`, `segments` array (each with `start_ms`, `end_ms`, `text`), `model`, `backend`, and `processing_time_ms`

Yêu cầu

  • Whisnap macOS app (download from whisnap.com)
  • Whisnap Cloud account (only if using --cloud flag)

Cài đặt

clawhub install neolio42/whisnap

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết